© 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. 44341
    Prev
    Next
    INDEX
    Explanations

    list categories and descriptions

    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
     expend
    0.53
     compromise
    0.52
     immobil
    0.50
    로
    0.49
     immobile
    0.46
    cri
    0.46
     the
    0.46
     tenho
    0.45
     иностран
    0.45
     extremely
    0.44
    POSITIVE LOGITS
    敨
    0.46
     標準
    0.45
    <unused82>
    0.45
    <unused42>
    0.44
    <unused27>
    0.44
    我们要
    0.44
    <unused43>
    0.44
    ائیگی
    0.43
     மொத்தம்
    0.43
    抺
    0.43
    Activations Density 0.001%

    No Known Activations