© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47418
    Prev
    Next
    INDEX
    Explanations

    catching and capturing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;
    0.67
    тных
    0.64
    та
    0.63
    MIL
    0.63
    㩽
    0.62
     Tosc
    0.61
    ScriptInterface
    0.60
    PAN
    0.58
     observación
    0.58
    )^{*}
    0.57
    POSITIVE LOGITS
     glimpse
    0.83
    ne
    0.82
     caught
    0.81
     glimpses
    0.79
    d
    0.77
     catches
    0.76
     catch
    0.74
     Caught
    0.69
    捕
    0.69
     whiff
    0.67
    Activations Density 0.081%

    No Known Activations