© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 67435
    Prev
    Next
    INDEX
    Explanations

    statistical ranges and measurements

    np_acts-logits-general · gemini-2.5-flash-lite

    confidence intervals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    嶠
    0.46
     আরবি
    0.44
    ফর্ম
    0.43
    及其
    0.42
    Vaterpolo
    0.42
    dorm
    0.42
    agamanam
    0.41
    ষ্ক
    0.41
    ্দ
    0.40
    々に
    0.40
    POSITIVE LOGITS
     houses
    0.45
     Houses
    0.44
     casas
    0.43
     surgeons
    0.42
     boş
    0.42
    <td>
    0.39
     confe
    0.39
     court
    0.39
     imposes
    0.39
     NI
    0.39
    Activations Density 0.015%

    No Known Activations