© 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. 66693
    Prev
    Next
    INDEX
    Explanations

    introducing a reason

    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
    毉
    -2.61
    _
    -2.30
     этом
    -2.27
    ኹ
    -2.17
    魉
    -2.17
    または
    -2.16
    ви
    -2.14
    </sup>
    -2.13
     языке
    -2.11
    ?”
    -2.08
    POSITIVE LOGITS
    I
    3.02
    *}[
    2.81
    C
    2.70
    
    2.64
    ‘
    2.48
    P
    2.41
    琑
    2.39
    providedIn
    2.38
    with
    2.33
    arynx
    2.27
    Activations Density 0.031%

    No Known Activations