© 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. 121409
    Prev
    Next
    INDEX
    Explanations

    materials and technical processes

    np_acts-logits-general · gemini-2.5-flash-lite

    specific terms followed by punctuation

    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
    গণ
    0.50
     `=`,
    0.50
     spä
    0.49
     rechnen
    0.48
     Spre
    0.47
     Bells
    0.46
     raus
    0.45
    abets
    0.45
     Eins
    0.44
     creeks
    0.44
    POSITIVE LOGITS
    Marriage
    0.49
     అమ్మ
    0.44
    important
    0.43
    脅
    0.43
     मुखिया
    0.43
    Related
    0.43
    reicher
    0.43
     кеңсесинде
    0.42
    Steel
    0.42
    overl
    0.42
    Activations Density 0.000%

    No Known Activations