© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202267
    Prev
    Next
    INDEX
    Explanations

    egg containing mutation

    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
    declar
    0.53
     قي
    0.52
     declara
    0.50
    ientes
    0.48
     يكون
    0.48
    ج
    0.46
    钏
    0.46
    ധാ
    0.45
    غب
    0.45
     برو
    0.45
    POSITIVE LOGITS
    ESH
    0.47
     Himalayan
    0.46
     UTF
    0.43
    UTF
    0.42
    QL
    0.41
    mashtami
    0.41
     EGFR
    0.41
     Eternal
    0.40
    OBI
    0.40
    ROUND
    0.40
    Activations Density 0.002%

    No Known Activations