© 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. 111568
    Prev
    Next
    INDEX
    Explanations

    links to download

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

    scripting and formatting conventions

    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
     미리
    0.60
     ")
    0.55
    จ
    0.54
    은
    0.50
    >");
    0.49
     !")
    0.49
     "))
    0.48
    ")
    0.47
    는
    0.47
     yrs
    0.46
    POSITIVE LOGITS
     moléculas
    0.51
     Gründung
    0.47
     dakkh
    0.47
    adaya
    0.46
     humanos
    0.44
    mAb
    0.43
    plasia
    0.42
    gha
    0.42
     человеку
    0.42
     Messiah
    0.41
    Activations Density 0.002%

    No Known Activations