© 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. 11662
    Prev
    Next
    INDEX
    Explanations

    The SS, following last

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

    reasoning behind

    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
     היו
    0.52
    ̀m
    0.51
    usión
    0.49
     긴
    0.48
     türk
    0.47
     iluminación
    0.47
    conoc
    0.46
    𝙚
    0.46
     уровень
    0.46
    은
    0.45
    POSITIVE LOGITS
     przysz
    0.49
     Dominica
    0.47
    好き
    0.45
    utcnow
    0.44
    ヒ
    0.44
     DBC
    0.44
     penggem
    0.44
     futurs
    0.43
     ZR
    0.43
    لیک
    0.42
    Activations Density 0.000%

    No Known Activations