© 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-262K
    7. 11290
    Prev
    Next
    INDEX
    Explanations

    principal and formulas

    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
    }^{+}$.
    0.47
     मेथड
    0.43
    settes
    0.42
     campsites
    0.41
    秙
    0.41
    釭
    0.40
    footed
    0.39
    ())).
    0.39
    」。
    0.39
     campsite
    0.39
    POSITIVE LOGITS
     Sequelize
    0.38
     AUTHORS
    0.38
    スポーツ
    0.36
     ujarnya
    0.36
    超出
    0.36
    ერი
    0.34
     PUP
    0.34
    从小
    0.33
     பேரும்
    0.33
    P
    0.32
    Activations Density 0.002%

    No Known Activations