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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 57421
    Prev
    Next
    INDEX
    Explanations

    nation, reputation, stories, causes, war

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

    The neuron fires on subjective, evaluative words—especially strong opinionated adjectives and adverbs expressing judgments or commentary.

    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
     еще
    -1.55
     criticized
    -1.34
     придется
    -1.34
     specialized
    -1.32
     серьез
    -1.26
     analyzed
    -1.23
     analyze
    -1.16
     вперед
    -1.16
     realize
    -1.16
     emphasized
    -1.13
    POSITIVE LOGITS
    Whilst
    1.75
     Whilst
    1.52
     whilst
    1.48
    Firstly
    1.19
    Alongside
    1.16
    rasti
    1.13
     swat
    1.09
     одной
    1.09
     Firstly
    1.04
     wilfully
    1.03
    Activations Density 0.208%

    No Known Activations