© 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. 123395
    Prev
    Next
    INDEX
    Explanations

    completely

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

    not followed by state

    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
     남아
    0.55
    ース
    0.46
     জিজ্ঞাসাবাদ
    0.46
    naye
    0.46
     misconduct
    0.45
    튤
    0.45
    烏
    0.45
     établissement
    0.45
    gung
    0.44
     예배
    0.44
    POSITIVE LOGITS
     t
    0.63
     Active
    0.50
     S
    0.50
     int
    0.49
     sensors
    0.48
     Compton
    0.48
     INT
    0.47
     Integral
    0.47
    ...
    0.47
     Mass
    0.46
    Activations Density 0.001%

    No Known Activations