© 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. 188064
    Prev
    Next
    INDEX
    Explanations

    want to generate

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

    Therefore, need, topics, history

    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
     abroad
    0.48
     workers
    0.46
     \%)$
    0.44
     deform
    0.43
     workmen
    0.42
     arg
    0.42
     negligent
    0.41
     পারছে
    0.41
    缩小
    0.41
     relegated
    0.40
    POSITIVE LOGITS
     स्मार्ट
    0.51
     मेकअप
    0.49
    is
    0.48
    ආ
    0.48
     Direkt
    0.47
    ="|
    0.46
    !।
    0.46
     hingga
    0.45
    Ⓐ
    0.45
     полно
    0.45
    Activations Density 0.000%

    No Known Activations