© 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. 109561
    Prev
    Next
    INDEX
    Explanations

    file metadata

    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
    Kast
    -0.76
    tabilis
    -0.70
     Kast
    -0.70
    ucket
    -0.69
    ToFit
    -0.69
    🚊
    -0.68
    poy
    -0.68
    setopt
    -0.66
    カフェ
    -0.65
    rifty
    -0.65
    POSITIVE LOGITS
     generic
    0.76
     bort
    0.69
    Supply
    0.68
     Apare
    0.68
    绽
    0.67
    spawn
    0.65
    maxX
    0.64
     cien
    0.64
     scalar
    0.64
    verbs
    0.63
    Activations Density 0.061%

    No Known Activations