© 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. 118741
    Prev
    Next
    INDEX
    Explanations

    modify by hand

    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
     residentes
    -0.82
     квартира
    -0.81
     בנו
    -0.77
     biznes
    -0.76
     сня
    -0.75
    ikawa
    -0.74
    ☔
    -0.73
     świ
    -0.72
     Fraser
    -0.70
     beş
    -0.70
    POSITIVE LOGITS
    urende
    0.85
     podrán
    0.84
     actionTypes
    0.83
     polit
    0.82
    islation
    0.81
    oforte
    0.78
    jutsu
    0.78
     mz
    0.77
    dey
    0.76
    enek
    0.76
    Activations Density 0.003%

    No Known Activations