© 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. 2482
    Prev
    Next
    INDEX
    Explanations

    percentages and numbers

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

    ."""

    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
     ለአ
    0.29
    蔘
    0.28
    因子
    0.28
     COMPOUNDS
    0.27
     একত্রে
    0.26
    がか
    0.26
     RATE
    0.25
     영국
    0.25
    ULATION
    0.25
    伊
    0.25
    POSITIVE LOGITS
    lig
    0.31
    ork
    0.31
    org
    0.30
    lin
    0.30
    gn
    0.29
    lint
    0.29
    mt
    0.28
    ree
    0.28
    her
    0.28
    ining
    0.28
    Activations Density 0.000%

    No Known Activations