© 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. 30337
    Prev
    Next
    INDEX
    Explanations

    foreign language conjunctions

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

    disciples, Process, crying, unusual

    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
     систему
    0.47
    ном
    0.46
    CCc
    0.46
     ransomware
    0.45
     dismantled
    0.44
     ಪ್ರಾ
    0.43
    តា
    0.43
    💿
    0.43
     типа
    0.42
     схе
    0.42
    POSITIVE LOGITS
     ihrer
    0.45
     他们
    0.45
     nebude
    0.45
     jejich
    0.44
    زندگی
    0.43
     njihov
    0.42
     kvůli
    0.42
    有可能
    0.41
     karena
    0.41
    他们的
    0.41
    Activations Density 0.000%

    No Known Activations