© 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. 103218
    Prev
    Next
    INDEX
    Explanations

    names ending in dor endorf

    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
    '
    -2.72
     During
    -2.31
     Also
    -2.22
    .'
    -2.19
    ."
    -2.13
    ='
    -2.09
     ('
    -2.09
     '
    -2.09
     или
    -2.06
    =('
    -2.02
    POSITIVE LOGITS
    ↵
    3.05
    to
    2.89
    s
    2.33
     новым
    2.33
    si
    2.30
    2.25
     ”
    2.22
     供
    2.16
    re
    2.13
     thre
    2.09
    Activations Density 0.029%

    No Known Activations