© 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. 74263
    Prev
    Next
    INDEX
    Explanations

    talk about, plans for

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

    tailored options for them

    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
     savez
    0.50
    用的
    0.50
     electrophoresis
    0.47
     tanya
    0.45
     Meme
    0.44
    ऱ्या
    0.43
    使用的
    0.43
    猊
    0.43
     Avatar
    0.43
    更能
    0.42
    POSITIVE LOGITS
    ಕೊ
    0.52
    ⅔
    0.50
     צ
    0.48
    0
    0.47
     dissidents
    0.47
     impasse
    0.45
    を引き
    0.45
    ையம்
    0.45
     enl
    0.45
     Ø
    0.44
    Activations Density 0.000%

    No Known Activations