© 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. 129611
    Prev
    Next
    INDEX
    Explanations

    appeal from the united states district court for the

    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
    </b>
    -1.85
     how
    -1.52
    ates
    -1.48
    v
    -1.42
     enough
    -1.42
     where
    -1.41
     Saltar
    -1.40
    </i>
    -1.38
    どうなる
    -1.38
    整整
    -1.34
    POSITIVE LOGITS
    牁
    1.62
    稣
    1.58
        
    1.58
    ⅝
    1.58
     anstatt
    1.55
    sekten
    1.55
    ꦶ
    1.48
     rús
    1.47
     ofreci
    1.44
     zubere
    1.44
    Activations Density 0.080%

    No Known Activations