© 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. 8748
    Prev
    Next
    INDEX
    Explanations

    null, none, empty

    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
    ಾನೂ
    0.37
     เด้อ
    0.37
     HEAT
    0.36
    »:
    0.35
     COMB
    0.35
     devez
    0.34
     EDITION
    0.34
    मार्ग
    0.34
     CONSULT
    0.34
     पदार्थों
    0.33
    POSITIVE LOGITS
     ,
    0.35
    除非
    0.33
     空
    0.32
    为空
    0.32
    0.31
    avor
    0.31
     empty
    0.31
    <tr>
    0.30
    atever
    0.30
     unnamed
    0.29
    Activations Density 0.173%

    No Known Activations