© 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. 29375
    Prev
    Next
    INDEX
    Explanations

    Easter outreach

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

    splitting, directing, deciding

    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
    ائط
    0.48
    ార్
    0.47
    ö
    0.47
    انى
    0.46
    皇家
    0.46
     dagar
    0.44
     Bates
    0.44
    يكل
    0.44
     அளவில்
    0.43
    Һ
    0.43
    POSITIVE LOGITS
    E
    0.53
    ➽
    0.51
     velcro
    0.44
     brin
    0.44
    ንግ
    0.44
     giáo
    0.44
     hammock
    0.42
     episcop
    0.42
    쓸
    0.42
    EB
    0.41
    Activations Density 0.000%

    No Known Activations