© 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. 225684
    Prev
    Next
    INDEX
    Explanations

    spaced targets

    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
    阍
    0.42
     Dimensions
    0.41
     lỗi
    0.40
     kó
    0.40
    Rationale
    0.40
    ItemId
    0.39
     anteced
    0.39
    ErrorMessage
    0.39
     mó
    0.38
     ':'
    0.38
    POSITIVE LOGITS
    皆さん
    0.49
     spolupr
    0.46
     பலர்
    0.45
     टिश
    0.45
    afood
    0.44
     சிலர்
    0.44
    ils
    0.44
     कागज
    0.44
     esfuerzos
    0.43
    鞣
    0.43
    Activations Density 0.001%

    No Known Activations