© 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. 57778
    Prev
    Next
    INDEX
    Explanations

    directional phrases or legal terms

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

    more revered, enough resources, free account

    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
    u
    0.55
    UM
    0.51
    MS
    0.50
    <h2>
    0.46
    BC
    0.46
     Sino
    0.46
    truncated
    0.46
    <0x0D>
    0.45
     IIS
    0.45
    IIS
    0.44
    POSITIVE LOGITS
    บคุม
    0.53
     energie
    0.52
     casserole
    0.50
     انرژی
    0.50
     championnat
    0.50
     conformations
    0.50
     particuliers
    0.49
    ିକ
    0.49
    㤈
    0.48
     चैंपियनशिप
    0.48
    Activations Density 0.000%

    No Known Activations