© 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. 65327
    Prev
    Next
    INDEX
    Explanations

    expressing difference

    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
    eſ
    -2.63
     konkret
    -2.61
    푆
    -2.56
    說
    -2.55
     современного
    -2.53
    薆
    -2.45
     cette
    -2.45
    ––
    -2.36
    푉
    -2.36
    actéristi
    -2.34
    POSITIVE LOGITS
    ).
    3.05
     from
    2.41
    hasMoreElements
    2.33
    焙
    2.31
    стреча
    2.31
    ⑧
    2.28
     namun
    2.23
     than
    2.22
    $\%$
    2.20
    꺾
    2.20
    Activations Density 0.047%

    No Known Activations