© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59207
    Prev
    Next
    INDEX
    Explanations

    Apple company and its products

    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
    '
    -3.36
    ’
    -3.06
    *
    -2.73
    at
    -2.50
     ‘
    -2.38
    on
    -2.30
     
    -2.30
    ”
    -2.28
     '
    -2.25
    有一定的
    -2.19
    POSITIVE LOGITS
     convencer
    2.59
    Ꮨ
    2.58
    塤
    2.52
    𓄹
    2.48
    䉴
    2.48
    pulsera
    2.48
    噥
    2.47
    蟶
    2.47
    Počet
    2.45
    峮
    2.44
    Activations Density 0.017%

    No Known Activations