© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102424
    Prev
    Next
    INDEX
    Explanations

    Emerson, HPLC, Stow

    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
    .’
    -2.95
    ’
    -2.92
    ㉗
    -2.63
    檠
    -2.56
     )))
    -2.47
    ’，
    -2.45
    鐃
    -2.42
    ))).
    -2.36
    ,’
    -2.34
    Ꭳ
    -2.31
    POSITIVE LOGITS
    1
    3.77
    8
    3.39
    '
    3.17
    .
    3.09
    P
    2.94
    6
    2.92
    9
    2.84
    </h3>
    2.77
    7
    2.75
    4
    2.64
    Activations Density 0.078%

    No Known Activations