© 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. 92403
    Prev
    Next
    INDEX
    Explanations

    before and after sequences

    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
    ion
    -1.16
    "
    -1.11
    s
    -1.10
    ia
    -1.05
    ’
    -1.02
     /
    -0.99
    d
    -0.98
    !
    -0.97
    rn
    -0.95
     wahrscheinlich
    -0.94
    POSITIVE LOGITS
     وبعد
    1.34
    andafter
    1.30
     Reglas
    1.15
     tidur
    1.14
    Dopo
    1.13
    ">)</
    1.12
    **/
    1.11
    tiembre
    1.10
     dawn
    1.09
     sunrise
    1.09
    Activations Density 0.032%

    No Known Activations