© 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. 188578
    Prev
    Next
    INDEX
    Explanations

    from your

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

    ethically fraught request

    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
     Köz
    0.46
    Salon
    0.46
    萦
    0.42
     persön
    0.40
     dishonesty
    0.40
     교
    0.40
    ipan
    0.39
     zaś
    0.39
    үү
    0.39
    交换
    0.39
    POSITIVE LOGITS
     austere
    0.46
     calf
    0.44
     gamle
    0.44
     unassuming
    0.44
     porcine
    0.44
    aph
    0.43
     simbolo
    0.43
    ዖ
    0.42
    mittedly
    0.42
     glyph
    0.42
    Activations Density 0.001%

    No Known Activations