© 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. 91837
    Prev
    Next
    INDEX
    Explanations

    color, angle, prime

    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
     banques
    -0.72
    밴
    -0.71
     armament
    -0.68
    vick
    -0.66
    evaluation
    -0.65
     erase
    -0.65
     RELATED
    -0.63
    aos
    -0.63
     Served
    -0.63
     racket
    -0.63
    POSITIVE LOGITS
     Герма
    0.77
    Casa
    0.75
    三星
    0.73
     egna
    0.72
     samoz
    0.67
    Youth
    0.65
     terce
    0.65
    felder
    0.65
    higen
    0.64
     måned
    0.64
    Activations Density 0.047%

    No Known Activations