© 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. 21459
    Prev
    Next
    INDEX
    Explanations

    and compromisesUltimate concertray incidentwant your

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

    Dar es Salaam

    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
     آموزش
    0.51
    salaryfrom
    0.49
     பயிற்
    0.48
    𝗪
    0.48
    🜨
    0.48
    ir
    0.47
     اگلے
    0.46
     वित्त
    0.46
     अजून
    0.46
     দ্রব
    0.46
    POSITIVE LOGITS
    ↵
    0.53
     (
    0.53
    <0x0D>
    0.49
    、
    0.48
     chaude
    0.46
    MO
    0.43
     nigra
    0.42
     !=
    0.42
     tekint
    0.42
     lot
    0.41
    Activations Density 0.000%

    No Known Activations