© 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. 240968
    Prev
    Next
    INDEX
    Explanations

    waste time

    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
    зяй
    0.55
    살
    0.55
    함
    0.54
    лава
    0.53
    슬
    0.52
    쥴
    0.52
    스
    0.51
    음
    0.49
    함을
    0.49
    헤
    0.49
    POSITIVE LOGITS
     manchmal
    0.55
     Surname
    0.54
     Smartphone
    0.51
     transparent
    0.47
     efficace
    0.47
     became
    0.46
     vo
    0.46
     deriv
    0.46
     degrad
    0.46
     丶
    0.46
    Activations Density 0.000%

    No Known Activations