© 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. 3188
    Prev
    Next
    INDEX
    Explanations

    one more sort of

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

    describing components and actions

    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
    n
    0.68
    te
    0.66
    ton
    0.64
    r
    0.64
    v
    0.62
    k
    0.61
    ts
    0.60
    and
    0.59
    ir
    0.59
    ant
    0.59
    POSITIVE LOGITS
    쯜
    0.56
     হাসপাত
    0.55
    都被
    0.54
    夯
    0.53
    让她
    0.52
    厕
    0.52
    球
    0.51
    糙
    0.50
    度假
    0.50
     sanitizer
    0.50
    Activations Density 0.000%

    No Known Activations