© 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. 128515
    Prev
    Next
    INDEX
    Explanations

    levels often

    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
    ז
    0.55
    inded
    0.51
    ン
    0.48
     በጣም
    0.46
    gets
    0.46
    شنبه
    0.46
    ن
    0.44
     attracts
    0.44
     حوالي
    0.44
    راق
    0.43
    POSITIVE LOGITS
    h
    0.52
     ajud
    0.49
     Mich
    0.46
     naturale
    0.46
     উপায়
    0.46
     abh
    0.46
    ljanje
    0.45
    ání
    0.44
     Gluten
    0.43
     dalla
    0.43
    Activations Density 0.002%

    No Known Activations