© 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. 81401
    Prev
    Next
    INDEX
    Explanations

    beyond, labels, Game, tongue

    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
    ဴ
    0.49
    reen
    0.48
    。
    0.48
    setText
    0.45
    句
    0.45
    。",
    0.45
    是
    0.45
    は
    0.45
    '
    0.45
    亡
    0.43
    POSITIVE LOGITS
     சிறந்த
    0.49
     excellent
    0.49
     מג
    0.49
     littoral
    0.49
     incred
    0.47
     فرد
    0.47
     rigorous
    0.47
     আদ
    0.46
     reservoirs
    0.46
     mussels
    0.46
    Activations Density 0.002%

    No Known Activations