© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 231349
    Prev
    Next
    INDEX
    Explanations

    puff pastry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     variable
    0.47
    variable
    0.45
     X
    0.42
     voluntary
    0.42
    combined
    0.42
     الصوت
    0.41
     eight
    0.41
     رز
    0.40
     patente
    0.40
     x
    0.40
    POSITIVE LOGITS
     станет
    0.52
     supervivencia
    0.52
     representación
    0.50
     আবারও
    0.50
     стане
    0.49
     sugest
    0.47
     দেশকে
    0.47
     demostrado
    0.46
    йга
    0.46
     देगी
    0.45
    Activations Density 0.000%

    No Known Activations