© 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. 99662
    Prev
    Next
    INDEX
    Explanations

    conflict and persecution

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

    license terms

    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
    𝖗
    0.50
     പോലെ
    0.46
    PerTrial
    0.45
     那麼
    0.45
    𝓽
    0.45
     রেখেছেন
    0.44
     少し
    0.44
     эффект
    0.44
    isecond
    0.44
     與
    0.43
    POSITIVE LOGITS
     The
    0.46
    מ
    0.46
    ור
    0.44
    ajas
    0.44
    とにかく
    0.44
    ב
    0.43
    ע
    0.43
    жи
    0.43
    ம
    0.43
    াপ
    0.42
    Activations Density 0.000%

    No Known Activations