© 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. 2787
    Prev
    Next
    INDEX
    Explanations

    absence of data

    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
    {?>
    -0.94
     namens
    -0.93
    Ⓖ
    -0.86
     gård
    -0.82
    今度は
    -0.82
    használ
    -0.81
    <mask>
    -0.81
     länder
    -0.80
    ,',
    -0.80
     Dengan
    -0.80
    POSITIVE LOGITS
     nothing
    3.20
     none
    2.78
     no
    2.59
     null
    2.44
     None
    2.41
     NULL
    2.39
     nobody
    2.30
     never
    2.27
     neither
    2.25
     नहीं
    2.17
    Activations Density 0.070%

    No Known Activations