© 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. 79701
    Prev
    Next
    INDEX
    Explanations

    introduces general or typical cases

    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_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
     and
    -2.94
     or
    -1.85
     which
    -1.63
    ;
    -1.55
     including
    -1.43
    )=>{
    
    -1.43
     ......
    -1.41
     on
    -1.38
     '';
    -1.36
     .....
    -1.36
    POSITIVE LOGITS
     we
    2.75
     they
    2.28
     there
    2.05
    ,
    2.05
     it
    1.82
     you
    1.80
     normaux
    1.70
     lourdes
    1.68
     remplace
    1.63
    にほんブログ村
    1.60
    Activations Density 0.070%

    No Known Activations