© 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. 78929
    Prev
    Next
    INDEX
    Explanations

    requirement

    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
     ​
    -0.88
     truly
    -0.87
     profoundly
    -0.86
     curation
    -0.85
     façons
    -0.80
     made
    -0.80
      
    -0.79
    してしまう
    -0.78
    弱点
    -0.77
     what
    -0.77
    POSITIVE LOGITS
    :<
    1.18
    )<
    1.14
    <strong>
    1.07
    !<
    1.06
    avut
    1.04
    titial
    1.02
     другим
    1.01
    ?<
    1.00
     ong
    1.00
    ;<
    1.00
    Activations Density 0.003%

    No Known Activations