© 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. 82528
    Prev
    Next
    INDEX
    Explanations

    legal requirements

    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
     ziemlich
    -0.91
     mudou
    -0.87
    違います
    -0.84
    Aprove
    -0.84
     вже
    -0.84
     lingered
    -0.82
    起了
    -0.81
    を入力
    -0.81
    prisingly
    -0.81
     vůbec
    -0.81
    POSITIVE LOGITS
     adequate
    1.14
     sufficient
    1.10
    至少
    1.09
     capable
    1.06
    必ず
    1.04
    capable
    1.02
     must
    0.99
     shall
    0.99
     tại
    0.99
     securely
    0.98
    Activations Density 0.027%

    No Known Activations