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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60177
    Prev
    Next
    INDEX
    Explanations

    rad- 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
     कार
    -0.69
    ヘ
    -0.68
    klady
    -0.68
     міста
    -0.65
     sout
    -0.65
    ToPoint
    -0.65
     ziua
    -0.64
     年度
    -0.63
    exercises
    -0.63
     CV
    -0.63
    POSITIVE LOGITS
     آخرین
    0.84
    valeur
    0.79
     cięż
    0.77
    пута
    0.76
    有任何
    0.75
    SLO
    0.75
    octave
    0.75
     千葉
    0.74
    FormField
    0.74
    visiae
    0.74
    Activations Density 0.038%

    No Known Activations