© 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. 39000
    Prev
    Next
    INDEX
    Explanations

    cities grow

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

    his Chinese phrases

    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
     slows
    0.56
     textvariable
    0.55
     simulates
    0.53
     стране
    0.48
     collaborates
    0.47
     highlighted
    0.46
    ଫ
    0.46
    }((
    0.45
     threatens
    0.45
     underscored
    0.45
    POSITIVE LOGITS
    Grant
    0.52
    杓
    0.51
    烜
    0.49
    他的
    0.48
    媲
    0.47
    Rate
    0.47
    艺
    0.46
    脑
    0.46
    秾
    0.45
     Mardi
    0.45
    Activations Density 0.000%

    No Known Activations