© 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. 52487
    Prev
    Next
    INDEX
    Explanations

    companies decided

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

    subtly highlight

    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
    tei
    0.50
     Newborn
    0.46
    -*
    0.45
    0
    0.45
    ßen
    0.44
     newborn
    0.44
    ële
    0.44
    Cand
    0.44
    gol
    0.43
    ib
    0.42
    POSITIVE LOGITS
     calculateur
    0.59
     chinois
    0.58
     cherche
    0.58
     prestataire
    0.56
     correspondant
    0.54
     corrigir
    0.52
    м
    0.52
     ouvr
    0.52
     croire
    0.52
     climatique
    0.51
    Activations Density 0.000%

    No Known Activations