© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90210
    Prev
    Next
    INDEX
    Explanations

    professional advice and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invertir
    0.52
     unlawfully
    0.48
    ᅨ
    0.46
    ​,
    0.46
     efectuar
    0.45
     suffis
    0.44
     sufrir
    0.43
    <0xF3>
    0.43
     கிடைக்கும்
    0.42
     controlar
    0.42
    POSITIVE LOGITS
     presses
    0.49
    d
    0.45
     man
    0.44
    ۰
    0.43
     impressions
    0.42
    dě
    0.42
    /
    0.42
     narrow
    0.41
     Presses
    0.40
    kmale
    0.40
    Activations Density 0.003%

    No Known Activations