© 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. 190679
    Prev
    Next
    INDEX
    Explanations

    curling, chamber, hall

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

    lobes, extension, together, cup

    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
     جعل
    0.55
     філь
    0.52
     вважа
    0.52
    ‍♀️
    0.51
     séances
    0.49
    すす
    0.49
     احترام
    0.49
    failures
    0.47
     entrees
    0.47
     रजत
    0.47
    POSITIVE LOGITS
    id
    0.60
    u
    0.59
    ir
    0.56
    it
    0.52
    m
    0.48
    ran
    0.48
    is
    0.46
    粞
    0.46
    n
    0.46
    ner
    0.46
    Activations Density 0.000%

    No Known Activations