© 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. 248160
    Prev
    Next
    INDEX
    Explanations

    May sound, CO2, assignment, immediately

    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
    科學
    0.59
    󰡔
    0.47
    郋
    0.47
    Neo
    0.47
    壘
    0.47
    耒
    0.47
    विज्ञान
    0.46
    鉑
    0.46
    名稱
    0.46
    एस
    0.46
    POSITIVE LOGITS
     Matching
    0.45
     movable
    0.44
     banknotes
    0.44
     varm
    0.44
     Britons
    0.43
     False
    0.43
    тическая
    0.42
    is
    0.42
    agan
    0.42
    ากาศ
    0.42
    Activations Density 0.000%

    No Known Activations