© 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. 165972
    Prev
    Next
    INDEX
    Explanations

    specific prepositions and conjunctions

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

    cannot and policy

    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
    namespaces
    0.48
     identifiers
    0.47
     parameters
    0.47
     namespaces
    0.45
    ਰ
    0.45
     Enrichment
    0.44
     expertise
    0.43
    াচিত
    0.43
    ורה
    0.43
    Ꮶ
    0.43
    POSITIVE LOGITS
     ん
    0.50
    Kamu
    0.49
    ｡
    0.48
    음을
    0.44
     бывают
    0.44
    SOME
    0.43
    ²',
    0.43
     الدوري
    0.42
     kemungkinan
    0.42
     sposob
    0.42
    Activations Density 0.000%

    No Known Activations