© 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. 78595
    Prev
    Next
    INDEX
    Explanations

    card limit

    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
     beide
    0.52
    شن
    0.49
    衿
    0.48
    য়াম
    0.47
     അപകട
    0.47
    Encript
    0.47
    বঙ্গ
    0.46
    czne
    0.46
    ls
    0.45
    மேலும்
    0.45
    POSITIVE LOGITS
     Virtually
    0.48
     внутренних
    0.46
     내부
    0.45
    urchase
    0.45
    ữ
    0.43
    aturated
    0.43
     ১৯৪৭
    0.43
    GD
    0.41
    持有
    0.39
    顶部
    0.39
    Activations Density 0.000%

    No Known Activations