© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32142
    Prev
    Next
    INDEX
    Explanations

    code structure and testing

    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
     rokok
    -1.48
     entweder
    -1.45
    hehehe
    -1.43
     tejto
    -1.40
     avaient
    -1.38
     esat
    -1.36
     Queste
    -1.36
     embre
    -1.35
    truly
    -1.34
    この
    -1.34
    POSITIVE LOGITS
     when
    2.64
     with
    2.52
     without
    2.31
     and
    2.09
     despite
    2.08
     on
    1.95
     from
    1.91
     given
    1.83
     even
    1.79
     by
    1.71
    Activations Density 0.021%

    No Known Activations