© 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. 107451
    Prev
    Next
    INDEX
    Explanations

    child prostitution

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

    verily and lo

    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
     दरों
    0.52
     बँके
    0.48
    كوم
    0.48
    ъ
    0.47
    ід
    0.46
     deficits
    0.46
    äume
    0.46
     imao
    0.45
     deň
    0.45
    귿
    0.44
    POSITIVE LOGITS
     অনেকে
    0.46
    member
    0.44
    members
    0.43
     Nicola
    0.41
     Scientists
    0.41
     Bohemian
    0.41
    scientists
    0.41
     artistic
    0.40
    athletes
    0.40
    membership
    0.40
    Activations Density 0.001%

    No Known Activations