© 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. 137024
    Prev
    Next
    INDEX
    Explanations

    text sent to

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

    often describes or warns

    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
    IB
    0.50
    in
    0.49
    IV
    0.49
    col
    0.49
    w
    0.48
    AX
    0.48
    and
    0.47
     Estadual
    0.47
    ing
    0.46
    t
    0.46
    POSITIVE LOGITS
     pedestrian
    0.47
     cityscape
    0.47
     bathrobe
    0.46
     храм
    0.45
     triathlon
    0.44
     tweed
    0.44
    诸
    0.44
     playgrounds
    0.44
    시킨
    0.43
    시키는
    0.43
    Activations Density 0.001%

    No Known Activations