© 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. 48189
    Prev
    Next
    INDEX
    Explanations

    plan, analysis, characterized, multiples

    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
    ുവരി
    0.49
    Но
    0.48
    Huang
    0.48
    サル
    0.48
    Мар
    0.48
    India
    0.47
    Yeni
    0.47
    刘
    0.46
    ভারতীয়
    0.46
    그
    0.46
    POSITIVE LOGITS
     driven
    0.45
     salir
    0.43
    ers
    0.42
     με
    0.42
     echoed
    0.42
    ↵
    0.42
     matching
    0.41
     matched
    0.41
     στο
    0.41
     και
    0.40
    Activations Density 0.008%

    No Known Activations