© 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. 91453
    Prev
    Next
    INDEX
    Explanations

    words starting with ff or off

    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
    étal
    -0.74
     signora
    -0.73
     Sept
    -0.71
    ichtliche
    -0.69
    Defining
    -0.68
     fibonacci
    -0.67
    mem
    -0.67
    五
    -0.66
    FAVOR
    -0.66
    Matched
    -0.66
    POSITIVE LOGITS
     Aff
    0.92
    liff
    0.86
    ából
    0.84
     Basse
    0.82
     Upan
    0.79
    hearsal
    0.79
     aff
    0.79
     Tremb
    0.77
     couleur
    0.75
    iseta
    0.74
    Activations Density 0.030%

    No Known Activations