© 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. 52462
    Prev
    Next
    INDEX
    Explanations

    view full

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

    but, though

    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
    ająca
    0.45
     menuMobile
    0.45
     dietro
    0.42
    lastCursor
    0.41
    这张
    0.40
     lưới
    0.40
    内部
    0.40
    眦
    0.39
    lblName
    0.38
    形状
    0.38
    POSITIVE LOGITS
     Underwood
    0.42
     Heter
    0.39
     Theodore
    0.38
    reads
    0.38
     Merton
    0.38
     Elon
    0.37
     Susan
    0.37
     tom
    0.37
     Steven
    0.37
    ᆫ
    0.37
    Activations Density 0.000%

    No Known Activations