© 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. 10-GEMMASCOPE-RES-131K
    7. 40678
    Prev
    Next
    INDEX
    Explanations

    uploading files

    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_10/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
    }$
    -2.98
    k
    -2.66
    to
    -2.39
    {
    -2.22
     отличается
    -2.13
    What
    -2.11
    How
    -2.09
    i
    -2.06
     имел
    -2.06
    va
    -2.06
    POSITIVE LOGITS
    髫
    3.02
    〼
    2.73
    ⬈
    2.50
    ︲
    2.47
     onslaught
    2.41
     وتم
    2.38
    uploads
    2.34
     unsere
    2.34
    𖣔
    2.33
    茈
    2.31
    Activations Density 0.002%

    No Known Activations