© 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. 218823
    Prev
    Next
    INDEX
    Explanations

    cost, expenses, elimination

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

    kind of adjective question

    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
     Phenomenology
    0.47
    वारा
    0.46
    ',
    0.46
    ロボ
    0.45
    、“
    0.44
    ','"
    0.44
    *:
    0.44
    тан
    0.44
    深夜
    0.43
    cience
    0.42
    POSITIVE LOGITS
    uí
    0.49
     Sumb
    0.48
    rax
    0.47
     comp
    0.46
     수행
    0.45
     這
    0.44
     ćemo
    0.43
     Phó
    0.43
     ಸ್ಥಳ
    0.42
     Diput
    0.42
    Activations Density 0.001%

    No Known Activations