© 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. 179710
    Prev
    Next
    INDEX
    Explanations

    privacy website

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

    questions and studies

    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
     사랑
    0.48
    戀
    0.46
    的热
    0.45
    ဆို
    0.43
    ທາງ
    0.42
     gede
    0.41
    ான்
    0.41
    າດ
    0.41
    恋
    0.41
    滿足
    0.40
    POSITIVE LOGITS
    ittees
    0.46
     絵
    0.43
    DONT
    0.42
     Vieux
    0.42
     spettac
    0.42
    wett
    0.41
    Jlc
    0.41
    cm
    0.40
    starttime
    0.40
    してから
    0.40
    Activations Density 0.000%

    No Known Activations