© 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. 175492
    Prev
    Next
    INDEX
    Explanations

    programs, remaining

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

    describing features or qualities

    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
     errori
    0.52
     The
    0.51
     A
    0.49
    indeki
    0.48
    Written
    0.47
     ond
    0.46
     Dund
    0.46
    C
    0.46
     OBS
    0.45
     Group
    0.44
    POSITIVE LOGITS
     улы
    0.46
     энерги
    0.43
    ेंगू
    0.41
     transparencia
    0.41
    hygine
    0.41
     kilowatt
    0.40
     वनस्पती
    0.40
     photosynthetic
    0.39
     liberté
    0.39
     револю
    0.39
    Activations Density 0.004%

    No Known Activations