© 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. 16-GEMMASCOPE-2-RES-262K
    7. 34809
    Prev
    Next
    INDEX
    Explanations

    nexus repository, VX US, crux aves

    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_16_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
     be
    1.12
    <0x80>
    0.83
     febrero
    0.77
    личество
    0.71
    ၃
    0.71
     سي
    0.70
     أحمد
    0.70
    oš
    0.69
    ية
    0.68
     habla
    0.68
    POSITIVE LOGITS
    ↵↵
    0.93
     -
    0.89
    м
    0.88
    ↵↵↵
    0.84
    م
    0.83
    ların
    0.78
    .
    0.78
    म
    0.78
    र
    0.77
     interplay
    0.76
    Activations Density 0.000%

    No Known Activations