© 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. 8848
    Prev
    Next
    INDEX
    Explanations

    class definitions and programming constructs

    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
    </i>
    -1.87
     provenientes
    -1.66
    因为他
    -1.63
     conocidos
    -1.52
    紧接着
    -1.45
     ofrecemos
    -1.41
     cincuenta
    -1.41
    場に
    -1.40
     esame
    -1.38
    ⸢
    -1.38
    POSITIVE LOGITS
    including
    1.80
    衎
    1.72
    from
    1.66
    จาก
    1.60
     Including
    1.59
     [],
    1.59
    也
    1.59
    }
    1.57
    沨
    1.54
     ändern
    1.52
    Activations Density 0.006%

    No Known Activations