© 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. 150411
    Prev
    Next
    INDEX
    Explanations

    founding texts

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

    logos, brand, safety, principles

    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
     საშ
    0.49
     ഒരാ
    0.49
     ದೊ
    0.47
    fer
    0.46
    )}-
    0.45
     Haunted
    0.44
    Naissance
    0.43
     Tian
    0.43
     Mudah
    0.43
     haunted
    0.42
    POSITIVE LOGITS
    вы
    0.63
    ی
    0.63
    ITH
    0.61
    ের
    0.55
     INTERNAL
    0.55
    s
    0.55
    罌
    0.55
     impact
    0.53
     оно
    0.52
    OLOGY
    0.51
    Activations Density 0.000%

    No Known Activations