© 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. 70698
    Prev
    Next
    INDEX
    Explanations

    types of frozen things

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

    describing places or food ingredients

    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
     الفترة
    0.41
    CHARACTER
    0.40
     دب
    0.40
     خط
    0.39
    CellValue
    0.39
    enheim
    0.39
    對於
    0.37
    鳌
    0.37
     tekint
    0.37
     Costume
    0.36
    POSITIVE LOGITS
     пше
    0.50
    नाती
    0.43
    frozen
    0.42
     congel
    0.42
     Router
    0.41
    зил
    0.41
     froze
    0.41
     routers
    0.40
     freezes
    0.40
    Router
    0.39
    Activations Density 0.012%

    No Known Activations