© 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. 43730
    Prev
    Next
    INDEX
    Explanations

    head and roles, parts, or actions

    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
    vantaged
    -3.94
    u
    -3.41
    (
    -3.36
    I
    -3.34
    e
    -3.31
    ”
    -2.97
    th
    -2.80
    "
    -2.70
     –
    -2.70
    <i>
    -2.70
    POSITIVE LOGITS
    ଝ
    3.89
    淠
    3.63
    ㍑
    3.55
     zoude
    3.31
    彞
    3.27
     wth
    3.20
    檍
    3.20
    凩
    3.19
    蔀
    3.19
    ﹍﹍
    3.11
    Activations Density 0.032%

    No Known Activations