© 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. 49407
    Prev
    Next
    INDEX
    Explanations

    small mailbox

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

    abstracts, summaries, or explanations

    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
     Tüm
    0.52
    一脸
    0.51
     кілька
    0.46
    ുകൂ
    0.45
    ྪ
    0.44
     választ
    0.44
    โจ
    0.44
     Acerca
    0.44
    뽑
    0.44
     deuxième
    0.43
    POSITIVE LOGITS
     twisting
    0.52
    ots
    0.49
     biscuit
    0.48
     chips
    0.47
     MUS
    0.47
     hammock
    0.46
     MEX
    0.46
    Continue
    0.46
     horse
    0.45
     equestrian
    0.45
    Activations Density 0.000%

    No Known Activations