© 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. 150360
    Prev
    Next
    INDEX
    Explanations

    off guard, after task, person accessing

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

    conceptual description

    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
    0
    0.57
    3
    0.52
    4
    0.48
    etti
    0.47
     coincident
    0.46
    2
    0.45
     by
    0.44
    6
    0.44
     Demi
    0.44
    ette
    0.44
    POSITIVE LOGITS
     早
    0.51
     estados
    0.50
     jantar
    0.50
     infrastrukt
    0.50
     compone
    0.50
     müz
    0.49
    kowego
    0.48
    HasStarred
    0.48
     আজকে
    0.47
     也
    0.47
    Activations Density 0.000%

    No Known Activations