© 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. 124624
    Prev
    Next
    INDEX
    Explanations

    contact us

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

    concepts and constraints

    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
    巻き
    0.57
     humbled
    0.51
    材
    0.50
    を行
    0.48
    Birmingham
    0.47
     fantastical
    0.47
    блі
    0.47
     specie
    0.46
    山の
    0.46
     Alph
    0.46
    POSITIVE LOGITS
    '
    0.52
     您
    0.49
     actualizaciones
    0.49
    ுற
    0.48
    ontiti
    0.48
     更新
    0.47
     atualizar
    0.46
    forcement
    0.45
    وان
    0.45
    npcs
    0.43
    Activations Density 0.000%

    No Known Activations