© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 120339
    Prev
    Next
    INDEX
    Explanations

    parasite processes, missing persons, Drive your, sponsor, issue of

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

    code and pastry

    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
    ί
    0.49
    孝
    0.44
     Improves
    0.43
    ग्रेड
    0.43
     الكتاب
    0.42
     Doll
    0.42
    steuer
    0.42
    ೮
    0.42
    ിക
    0.40
     Wish
    0.40
    POSITIVE LOGITS
    !</
    0.44
    !\
    0.41
    biome
    0.41
    asd
    0.41
    णाचा
    0.41
    !",
    0.40
     አካ
    0.40
    ASF
    0.40
    ?!"
    0.40
    !");
    0.40
    Activations Density 0.000%

    No Known Activations