© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108634
    Prev
    Next
    INDEX
    Explanations

    testing and technical terms

    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
     }}}
    -0.87
     dirty
    -0.77
     weißt
    -0.76
    newpage
    -0.75
     Bewegung
    -0.75
    ssystem
    -0.73
    Bottom
    -0.71
     לי
    -0.69
     something
    -0.69
     Wunsch
    -0.69
    POSITIVE LOGITS
     Zav
    0.76
    ФА
    0.75
     Dividend
    0.74
    吸引
    0.73
    jamientos
    0.69
     perceptual
    0.69
    HTC
    0.68
     ня
    0.68
     rule
    0.68
    tru
    0.67
    Activations Density 0.016%

    No Known Activations