© 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. 22-GEMMASCOPE-RES-131K
    4. 104470
    Prev
    Next
    INDEX
    Explanations

    qualities and characteristics

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

    The neuron selectively activates on rich, polysyllabic adjectives used as strong evaluative descriptors.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     such
    -1.37
     you
    -1.28
    About
    -1.09
     głównie
    -1.09
     what
    -1.08
     about
    -1.08
     including
    -1.05
     skóra
    -1.05
     Pferd
    -1.05
    Види
    -1.04
    POSITIVE LOGITS
    และ
    1.97
     and
    1.80
     защото
    1.37
    ttin
    1.31
     و
    1.30
    вут
    1.30
    ֺ
    1.29
    它
    1.28
    kawas
    1.26
    ⚢
    1.26
    Activations Density 0.015%

    No Known Activations