© 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. 134421
    Prev
    Next
    INDEX
    Explanations

    covered disagreement agree International box educator managed Window after

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

    originally, most, again

    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
    ése
    0.49
    னி
    0.48
    noz
    0.46
    ine
    0.46
    mse
    0.46
    less
    0.45
    ínu
    0.44
    %、
    0.44
    íny
    0.44
    ied
    0.44
    POSITIVE LOGITS
     carico
    0.54
     éclair
    0.48
    τύ
    0.47
     punctul
    0.47
     dotato
    0.47
     allev
    0.47
     assinatura
    0.47
     tabela
    0.46
     قادر
    0.46
     prenot
    0.46
    Activations Density 0.001%

    No Known Activations