© 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. 30351
    Prev
    Next
    INDEX
    Explanations

    J.C. followed by name

    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
    んですか
    -0.81
     Shoreline
    -0.79
    ophosph
    -0.79
    localVar
    -0.78
     beatles
    -0.77
     vespa
    -0.77
     brauche
    -0.75
     slan
    -0.73
     eiffel
    -0.72
    镲
    -0.72
    POSITIVE LOGITS
     JC
    0.89
     into
    0.70
     pasted
    0.69
     jc
    0.69
     ere
    0.69
    jc
    0.68
     podob
    0.67
     Opinion
    0.65
    ungu
    0.65
    POA
    0.64
    Activations Density 0.021%

    No Known Activations