© 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. 90369
    Prev
    Next
    INDEX
    Explanations

    team / focus / role / strategy

    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
     Али
    0.47
    ພວກເຮ
    0.46
     этом
    0.45
    ExprNode
    0.45
    鄯
    0.45
     נוס
    0.45
     અમારી
    0.45
    骖
    0.45
     этой
    0.44
     οποία
    0.43
    POSITIVE LOGITS
    的
    0.50
    r
    0.46
    ie
    0.46
     boli
    0.43
    ler
    0.42
    خ
    0.42
    he
    0.41
    the
    0.41
    ू
    0.41
    <0xA2>
    0.40
    Activations Density 0.002%

    No Known Activations