© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12426
    Prev
    Next
    INDEX
    Explanations

    noun categories and descriptors

    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_262k_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
    𝗶
    0.44
    -">
    0.40
    𝗬
    0.40
    𝙄
    0.37
     disqualify
    0.37
    𝗗
    0.37
    이를
    0.36
    𝗧
    0.36
    BOOL
    0.35
    িগুণ
    0.35
    POSITIVE LOGITS
     extraordinaire
    0.42
    ாம்
    0.39
    celona
    0.37
    ρεία
    0.35
     simbolo
    0.34
     llamadas
    0.34
    黉
    0.33
     Ern
    0.32
    chanics
    0.32
    ское
    0.32
    Activations Density 0.213%

    No Known Activations