© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 60419
    Prev
    Next
    INDEX
    Explanations

    definitions in documents

    np_acts-logits-general · gemini-2.5-flash-lite

    potentially violent obsession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <0x80>
    0.52
     soundtracks
    0.48
     songs
    0.46
     removes
    0.46
    젼
    0.46
     refused
    0.45
     an
    0.45
    ت
    0.45
     Strasbourg
    0.44
     unaffected
    0.44
    POSITIVE LOGITS
    じて
    0.50
     अगला
    0.46
    ็อก
    0.45
    Brien
    0.45
     फीसदी
    0.43
    icht
    0.43
     विश
    0.43
     विश्वास
    0.43
     เหลือ
    0.42
    <unused967>
    0.41
    Activations Density 0.000%

    No Known Activations