© 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. 46958
    Prev
    Next
    INDEX
    Explanations

    gift bag

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

    conveys imitation limit captures

    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
    始まる
    0.41
     japonesa
    0.41
    $&
    0.40
    ネジ
    0.40
    iliano
    0.40
    िल
    0.40
     tanto
    0.39
     Ngh
    0.39
    jaan
    0.39
     religiosa
    0.39
    POSITIVE LOGITS
     histoires
    0.51
    𝗺
    0.51
    ORA
    0.50
    Retour
    0.50
    恂
    0.49
     coût
    0.48
    ્રોલ
    0.48
    镗
    0.48
     ölç
    0.47
     архів
    0.47
    Activations Density 0.000%

    No Known Activations