© 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-16K
    7. 12685
    Prev
    Next
    INDEX
    Explanations

    catch up, track progress

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

    tracking and following

    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_16k_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
     persistence
    0.47
     restraint
    0.47
     />
    0.46
    persistence
    0.43
    меры
    0.42
    工作室
    0.42
    вере
    0.42
    $,
    0.42
    injured
    0.42
     لاحظوا
    0.42
    POSITIVE LOGITS
     kịp
    0.68
    h
    0.61
     catches
    0.59
     catch
    0.55
     keting
    0.54
     catching
    0.53
     updates
    0.52
    节奏
    0.52
     Catch
    0.51
     track
    0.50
    Activations Density 0.237%

    No Known Activations