© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 62441
    Prev
    Next
    INDEX
    Explanations

    knowledge management, king, market cap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;
    0.59
    rok
    0.53
    ście
    0.52
    steacher
    0.51
    ang
    0.51
    lek
    0.51
    }.
    0.50
    ás
    0.50
    ills
    0.50
    ess
    0.49
    POSITIVE LOGITS
    REME
    0.49
     PRODU
    0.49
    ¯</
    0.46
    釹
    0.46
    UWORD
    0.44
    CENTER
    0.44
     rodean
    0.44
    ್ರೀ
    0.43
     zid
    0.43
    érieures
    0.42
    Activations Density 0.003%

    No Known Activations