© 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. 174603
    Prev
    Next
    INDEX
    Explanations

    blue haze, smoker box, composite decking

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

    geology

    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
    Authors
    0.57
     Literature
    0.53
     Saying
    0.53
     Lobkowicz
    0.53
     Translated
    0.52
    يدا
    0.51
    Translated
    0.51
    炭
    0.51
    كتب
    0.50
    Result
    0.50
    POSITIVE LOGITS
     geological
    0.51
     geology
    0.49
     ecology
    0.47
     geologist
    0.46
     geologic
    0.46
     togg
    0.46
     to
    0.45
     glacier
    0.44
    .}$
    0.44
    ಲಿಯ
    0.44
    Activations Density 0.001%

    No Known Activations