© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73667
    Prev
    Next
    INDEX
    Explanations

    division followed by identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    亮的
    -0.99
    ettür
    -0.94
    jetivos
    -0.94
    콴
    -0.92
    וקה
    -0.92
    ादी
    -0.92
    那位
    -0.91
    pV
    -0.90
    owych
    -0.90
    逦
    -0.90
    POSITIVE LOGITS
     of
    1.40
    m
    1.23
    al
    1.22
    ally
    1.19
    ary
    1.16
    但她
    1.09
     pero
    1.05
    但
    1.04
    naire
    1.03
    als
    1.02
    Activations Density 0.015%

    No Known Activations