© 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. 137100
    Prev
    Next
    INDEX
    Explanations

    key aspects or CSA purchase

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

    bodybuilding; essential

    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
     نهر
    0.52
    ’
    0.51
     y
    0.51
     acqua
    0.49
     n
    0.48
     tule
    0.48
     ponte
    0.48
     flex
    0.47
     zur
    0.47
     nach
    0.46
    POSITIVE LOGITS
     Бү
    0.54
    Ϲ
    0.49
    nsp
    0.47
    ϳ
    0.47
    ேச
    0.46
    ोनेशिया
    0.46
     どう
    0.45
    =+
    0.45
    carotene
    0.43
    Ὑ
    0.43
    Activations Density 0.000%

    No Known Activations