© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32392
    Prev
    Next
    INDEX
    Explanations

    date; morality; his

    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
    lessly
    -0.81
    相談
    -0.76
    اكم
    -0.75
     baca
    -0.73
     cioc
    -0.73
     puo
    -0.73
     fuq
    -0.73
     konsult
    -0.73
     Lichten
    -0.72
    thunk
    -0.72
    POSITIVE LOGITS
     Peter
    0.78
    ując
    0.74
    ko
    0.74
     delaying
    0.73
    TagNumber
    0.72
     confirm
    0.72
    }$\\
    0.71
     stalling
    0.71
    uş
    0.71
     escaped
    0.71
    Activations Density 0.012%

    No Known Activations