© 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. 251071
    Prev
    Next
    INDEX
    Explanations

    calendar was, includes operation, respecting tradition

    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
     człon
    0.46
    ütte
    0.45
     accession
    0.45
    "}}
    0.45
    圍
    0.45
     OPCODE
    0.44
    لك
    0.43
    㳒
    0.43
     Legendre
    0.42
    괵
    0.42
    POSITIVE LOGITS
    மி
    0.52
    ishwarya
    0.48
     zoomed
    0.46
     truthfully
    0.46
    rut
    0.46
    asic
    0.46
    yuk
    0.46
     as
    0.46
    liv
    0.45
    丑
    0.44
    Activations Density 0.001%

    No Known Activations