© 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. 22-GEMMASCOPE-RES-131K
    7. 34912
    Prev
    Next
    INDEX
    Explanations

    timestamp

    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_22/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
     The
    -2.89
     This
    -2.64
    苤
    -2.50
     I
    -2.50
     VERY
    -2.48
     "
    -2.36
     durante
    -2.34
     Granted
    -2.30
     "(
    -2.28
    就跟
    -2.28
    POSITIVE LOGITS
     untuk
    2.22
    ၟ
    2.19
    इटम
    2.19
    푣
    2.17
    鱘
    2.14
     drau
    2.09
    珢
    2.09
    趼
    2.08
    ஂ
    2.06
     zina
    2.03
    Activations Density 0.004%

    No Known Activations