© 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. 10-GEMMASCOPE-RES-131K
    7. 9473
    Prev
    Next
    INDEX
    Explanations

    under the influence of

    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
     the
    -1.60
    落ちる
    -1.46
    led
    -1.45
    夕方
    -1.42
    揸
    -1.39
     deliver
    -1.39
     soir
    -1.38
     who
    -1.36
    懸命
    -1.34
    凩
    -1.34
    POSITIVE LOGITS
    ↵
    1.77
    жения
    1.70
     reservados
    1.56
    }
    1.54
     misalnya
    1.53
     から
    1.52
     extremamente
    1.51
    Manbalar
    1.48
     moreover
    1.48
     myös
    1.47
    Activations Density 0.035%

    No Known Activations