© 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. 203258
    Prev
    Next
    INDEX
    Explanations

    made before

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

    battery life, still facing challenges

    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
     tá
    0.47
     end
    0.46
     ed
    0.45
     例如
    0.45
     e
    0.44
     Narrative
    0.44
    narr
    0.44
    tes
    0.43
     mate
    0.42
     Acqu
    0.42
    POSITIVE LOGITS
    IBR
    0.56
    כו
    0.56
    Bla
    0.55
    כ
    0.54
    چھ
    0.53
    Nuevo
    0.52
    Baj
    0.52
    h
    0.52
    છ
    0.52
    ќ
    0.50
    Activations Density 0.000%

    No Known Activations