© 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. 31584
    Prev
    Next
    INDEX
    Explanations

    following items

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

    prep time, cook time

    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
    唇
    0.48
    会の
    0.48
    ಞ
    0.47
    оз
    0.47
    ллин
    0.46
    номер
    0.46
     Muster
    0.45
    凪
    0.45
    クリー
    0.44
     Pierws
    0.44
    POSITIVE LOGITS
     knelt
    0.50
     inscreve
    0.47
     activité
    0.47
     perspectives
    0.46
     crossings
    0.46
     εκεί
    0.46
     lệ
    0.45
     жаңы
    0.45
     crosses
    0.44
     considérons
    0.44
    Activations Density 0.000%

    No Known Activations