© 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. 237378
    Prev
    Next
    INDEX
    Explanations

    output voltage, payment service, ceiling joists

    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
    रासत
    0.52
    riad
    0.46
    高品質
    0.46
    डीएम
    0.43
    ował
    0.42
    Drum
    0.42
    匣
    0.42
     تحریک
    0.41
    лкой
    0.40
    прово
    0.39
    POSITIVE LOGITS
     Giveen
    0.54
     vésicules
    0.51
     miatt
    0.49
     Ayrıca
    0.49
     verschil
    0.48
     Eine
    0.48
     raisons
    0.48
     expliquer
    0.47
     iskol
    0.47
     ह
    0.47
    Activations Density 0.001%

    No Known Activations