© 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. 75429
    Prev
    Next
    INDEX
    Explanations

    spelling and sound-alike variations

    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
     époque
    0.45
    덫
    0.44
    ン
    0.43
     célébr
    0.43
    ন
    0.42
     région
    0.41
     spéciale
    0.41
     lontano
    0.41
    綗
    0.41
     rôle
    0.41
    POSITIVE LOGITS
    urrection
    0.45
     لینا
    0.44
    的代码
    0.44
    向けの
    0.44
    的应用
    0.42
     government
    0.41
     genellikle
    0.41
     Health
    0.41
    icket
    0.41
    riva
    0.40
    Activations Density 0.011%

    No Known Activations