© 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. 66676
    Prev
    Next
    INDEX
    Explanations

    html class and id attributes

    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
    between
    -1.45
    انیا
    -1.28
     vuonna
    -1.26
     miasta
    -1.23
     gminy
    -1.22
     they
    -1.21
    łaj
    -1.19
    EditPart
    -1.19
    consulté
    -1.16
     intereses
    -1.16
    POSITIVE LOGITS
    瀟
    1.34
    がありますが
    1.26
     so
    1.24
     trazer
    1.18
     from
    1.17
    醞
    1.16
    clerosis
    1.14
     at
    1.14
    もあるので
    1.11
    很难
    1.10
    Activations Density 0.032%

    No Known Activations