© 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. 22-GEMMASCOPE-RES-131K
    7. 128955
    Prev
    Next
    INDEX
    Explanations

    titles, code snippets, and foreign words

    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_22/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
     for
    -1.34
     when
    -1.28
     When
    -1.26
     Besides
    -1.26
     While
    -1.21
     (
    -1.19
     Through
    -1.18
     at
    -1.18
     -
    -1.17
     by
    -1.14
    POSITIVE LOGITS
    
    1.25
     $\$$
    1.13
    <bos>
    1.10
     kalender
    1.09
     préparer
    1.09
     かわいい
    1.08
    staben
    1.08
     ſet
    1.07
     firſt
    1.06
    之类的
    1.06
    Activations Density 0.008%

    No Known Activations