© 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. 34-GEMMASCOPE-RES-131K
    7. 58595
    Prev
    Next
    INDEX
    Explanations

    operatic voice types

    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_34/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
     PARAMETERS
    -0.78
     }}\
    -0.74
    זה
    -0.71
    loggen
    -0.69
    }}\
    -0.69
     SCENE
    -0.68
    тать
    -0.67
    POSIX
    -0.66
    mitteilung
    -0.66
    ivot
    -0.66
    POSITIVE LOGITS
     tenor
    3.25
     soprano
    2.97
     Tenor
    2.28
     sop
    2.25
     bass
    2.23
    tenor
    2.22
    sop
    2.22
     Soprano
    2.17
    Tenor
    2.13
     baritone
    2.06
    Activations Density 0.037%

    No Known Activations