© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48800
    Prev
    Next
    INDEX
    Explanations

    articles and determiners

    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
    iak
    -0.87
    ᆼ
    -0.86
    ويد
    -0.85
    eronau
    -0.83
    いかがでしょうか
    -0.83
    种子
    -0.82
    フォーマンス
    -0.82
    Aura
    -0.81
    кування
    -0.81
    があって
    -0.80
    POSITIVE LOGITS
     THE
    1.22
    THE
    1.21
    the
    1.05
     a
    1.02
     some
    0.98
     an
    0.95
     the
    0.94
     definite
    0.93
     AN
    0.85
    The
    0.80
    Activations Density 0.034%

    No Known Activations