© 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. 36025
    Prev
    Next
    INDEX
    Explanations

    information reception and processing

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

    differential calculus

    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
     Colle
    0.48
    logback
    0.46
    andelier
    0.45
    害者
    0.44
     সামরিক
    0.44
     నేపథ
    0.44
    蚯
    0.43
     কোম্প
    0.43
    포츠
    0.43
    𒆷
    0.43
    POSITIVE LOGITS
     to
    0.46
     prec
    0.43
     individual
    0.42
    0.41
     exited
    0.41
     réduit
    0.41
     transported
    0.41
     oddly
    0.40
     was
    0.40
     individualized
    0.40
    Activations Density 0.000%

    No Known Activations