© 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. 120177
    Prev
    Next
    INDEX
    Explanations

    other information required

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

    SpaceX, within, morphine, sterile, racial, on, If, local, Unique

    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
    Preis
    0.47
    ۶
    0.47
     altında
    0.46
    Thi
    0.45
    INGRE
    0.45
    𝙸
    0.45
    Тре
    0.44
    Thông
    0.44
    ގ
    0.43
    Precio
    0.43
    POSITIVE LOGITS
    ant
    0.51
    olites
    0.50
    iliation
    0.48
     leech
    0.48
     যেকোনো
    0.47
    ography
    0.47
    aly
    0.47
    rit
    0.46
    okeh
    0.46
    camore
    0.46
    Activations Density 0.000%

    No Known Activations