© 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. 244607
    Prev
    Next
    INDEX
    Explanations

    specifico

    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
    意
    0.46
     highs
    0.46
     lows
    0.45
     disruption
    0.42
    ruption
    0.42
     Copeland
    0.41
    keye
    0.41
    CreateModel
    0.41
    不足
    0.40
    抜
    0.40
    POSITIVE LOGITS
     específica
    0.54
     Sulf
    0.52
     specifiche
    0.51
     suivant
    0.51
     huit
    0.49
     específico
    0.49
     Lào
    0.49
     spécifique
    0.47
    ōng
    0.47
    ओ
    0.46
    Activations Density 0.001%

    No Known Activations