© 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. 58007
    Prev
    Next
    INDEX
    Explanations

    flat followed by specific words

    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
    Њ
    -0.78
     избе
    -0.75
    права
    -0.74
    <0x89>
    -0.72
    ENTAL
    -0.72
     acredita
    -0.71
    orado
    -0.70
    чі
    -0.70
     ulaş
    -0.69
     fuite
    -0.68
    POSITIVE LOGITS
     Flat
    1.63
    flat
    1.60
    Flat
    1.59
     flat
    1.49
    tish
    1.38
    ulence
    1.23
     FLAT
    1.16
    ulent
    1.15
    FLAT
    1.02
     flattening
    1.02
    Activations Density 0.013%

    No Known Activations