© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 47954
    Prev
    Next
    INDEX
    Explanations

    NH abbreviations and uses

    np_acts-logits-general · gemini-2.5-flash-lite

    abbreviations in parentheses, particularly those in scientific or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is highly sensitive to uppercase acronyms, initialisms, and other multi‐letter technical or code‐style identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HOSTS
    -0.80
    cannot
    -0.73
    HJ
    -0.71
    apparently
    -0.71
    thiet
    -0.70
    icit
    -0.69
    paroles
    -0.68
     сколько
    -0.68
    Appearance
    -0.67
    Cannot
    -0.67
    POSITIVE LOGITS
     NH
    4.47
    NH
    4.28
     nh
    3.78
    nh
    3.73
     Nh
    3.00
     NHS
    2.77
    Nh
    2.64
    NHS
    2.48
     Nah
    2.36
    nhs
    2.05
    Activations Density 0.017%

    No Known Activations