© 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. 240462
    Prev
    Next
    INDEX
    Explanations

    says, been, observing

    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
    r
    0.51
    ids
    0.47
    此前
    0.45
    蔡
    0.45
    认定
    0.44
    ta
    0.44
    self
    0.43
    rac
    0.43
    不少
    0.43
    e
    0.42
    POSITIVE LOGITS
    APPY
    0.57
     ตา
    0.55
     Veron
    0.51
     lặng
    0.51
    㢦
    0.51
     Iya
    0.50
     เหลือ
    0.50
     พิ
    0.50
     Vicki
    0.50
     காற்றின்
    0.49
    Activations Density 0.000%

    No Known Activations