© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60293
    Prev
    Next
    INDEX
    Explanations

    a catch or problem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    隙間
    -0.82
    녕
    -0.77
     bords
    -0.76
    accesso
    -0.75
    榘
    -0.75
    вшийся
    -0.74
    äischen
    -0.73
    ifie
    -0.72
     fà
    -0.71
     envie
    -0.68
    POSITIVE LOGITS
     catch
    4.91
    catch
    3.70
     catches
    3.31
     Catch
    3.22
    Catch
    3.14
     caveat
    2.75
     CATCH
    2.64
     kicker
    2.63
     twist
    2.61
     catching
    2.56
    Activations Density 0.105%

    No Known Activations