© 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. 86565
    Prev
    Next
    INDEX
    Explanations

    intermediary states and functions

    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
    '
    -2.61
    s
    -2.34
     wholesome
    -2.31
    4
    -2.31
    -
    -2.28
    𨭆
    -2.22
     schließen
    -2.22
    6
    -2.06
     untuk
    -1.98
     lösen
    -1.95
    POSITIVE LOGITS
    袮
    3.27
    呖
    2.77
    Ꮟ
    2.61
    it
    2.47
    蠓
    2.45
    )/
    2.39
    珢
    2.36
    霂
    2.36
    ઁ
    2.34
    )),
    2.33
    Activations Density 0.007%

    No Known Activations