© 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. 118757
    Prev
    Next
    INDEX
    Explanations

    indiscriminate barrel bomb

    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
     summer
    -0.93
    summer
    -0.88
     September
    -0.84
    umque
    -0.82
     October
    -0.81
    September
    -0.81
     November
    -0.80
     August
    -0.79
    November
    -0.78
    Summer
    -0.77
    POSITIVE LOGITS
     besie
    0.89
    ΕΝ
    0.88
    瘻
    0.83
     mari
    0.82
    雫
    0.82
     besieged
    0.80
    DESTROY
    0.80
    fontWeight
    0.80
     March
    0.78
     Tapia
    0.77
    Activations Density 0.002%

    No Known Activations