© 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. 80345
    Prev
    Next
    INDEX
    Explanations

    following certain words

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

    legal or varies significantly

    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
    ários
    0.50
    ις
    0.47
     Substituting
    0.46
    íč
    0.46
    érature
    0.44
    ḷ
    0.44
    ╽
    0.43
     scarcely
    0.43
    írus
    0.42
    ాల్సి
    0.41
    POSITIVE LOGITS
    म
    0.55
    (
    0.52
     colloidal
    0.48
    Chlor
    0.48
    َم
    0.48
    companion
    0.48
     platter
    0.47
    خور
    0.46
     berd
    0.46
     ملا
    0.46
    Activations Density 0.000%

    No Known Activations