© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118805
    Prev
    Next
    INDEX
    Explanations

    Objective-C/C++ class prefixes

    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
     and
    -1.16
     it
    -1.01
    eef
    -0.86
    ooh
    -0.85
     thậm
    -0.83
     algunas
    -0.83
    grate
    -0.83
    uxx
    -0.82
    aah
    -0.82
    awakeFromNib
    -0.82
    POSITIVE LOGITS
    公斤
    1.02
     those
    1.02
     quelli
    1.00
    those
    1.00
    lenme
    0.98
    Those
    0.98
     vienas
    0.97
    onatos
    0.97
    Truly
    0.92
     quei
    0.90
    Activations Density 0.070%

    No Known Activations