© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14259
    Prev
    Next
    INDEX
    Explanations

    prefixes plus suffixes

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

    summarization, translation, vulnerability, gastronomic, charger, inauguration

    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_16k_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
    د
    0.25
    ל
    0.25
    ﹙
    0.24
     של
    0.24
    Collider
    0.24
    涧
    0.24
     on
    0.23
     ऑन
    0.23
     Significantly
    0.23
    爌
    0.23
    POSITIVE LOGITS
     vieux
    0.29
     speaks
    0.25
     queda
    0.25
     rightly
    0.24
     secrétaire
    0.24
     ver
    0.24
     schöne
    0.24
    ಿತ್ತು
    0.24
    বাসী
    0.23
     gusto
    0.23
    Activations Density 0.066%

    No Known Activations