© 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. 24067
    Prev
    Next
    INDEX
    Explanations

    drawn to, relies on, Received her

    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
     mwaka
    0.43
     iyong
    0.43
     proizvoda
    0.41
     pouces
    0.40
     অনুষ্ঠ
    0.40
     रफ्तार
    0.39
     "";
    0.39
     SUV
    0.39
     \"%
    0.39
     Filipinos
    0.38
    POSITIVE LOGITS
    ут
    0.48
    二次
    0.43
    Comparing
    0.42
     цело
    0.41
    ще
    0.41
     intrinsically
    0.41
    Shard
    0.40
    近
    0.40
     corrobor
    0.39
    CHRIST
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.