© 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. 124441
    Prev
    Next
    INDEX
    Explanations

    ask the, revealed that, is a, winner!

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

    place my, searchable string, classic bank run, get a loan

    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
    ೨
    0.52
    훌
    0.52
    संच
    0.50
    हास
    0.50
    𝘀
    0.50
    枡
    0.49
    相邻
    0.49
    及び
    0.48
    지
    0.48
    fecha
    0.47
    POSITIVE LOGITS
     تي
    0.49
     painfully
    0.48
     rebellious
    0.48
     thing
    0.46
     carried
    0.45
    athin
    0.45
     nub
    0.44
     seems
    0.43
     descendants
    0.43
    0.43
    Activations Density 0.000%

    No Known Activations