© 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. 59237
    Prev
    Next
    INDEX
    Explanations

    do not rely upon

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

    always double-check important information

    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
     Beschreibung
    0.42
     प्रदान
    0.41
    嘮
    0.40
    +](=
    0.39
    ходов
    0.39
     Ambris
    0.39
     توضیح
    0.39
     وضاحت
    0.39
     आण
    0.38
    رمین
    0.38
    POSITIVE LOGITS
     doubted
    0.47
     contrasted
    0.45
    布
    0.43
     confidently
    0.42
     seconded
    0.41
    б
    0.41
     布
    0.40
     kontrast
    0.40
     いき
    0.40
     lonely
    0.40
    Activations Density 0.010%

    No Known Activations