© 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. 145963
    Prev
    Next
    INDEX
    Explanations

    donor to, insincere invitation, fuel for, research on

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

    technical terms and descriptions

    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
    groom
    0.57
    SYN
    0.51
    den
    0.49
    t
    0.49
    discrimin
    0.48
     BRANCH
    0.48
    .°
    0.48
    l
    0.47
    grav
    0.46
    lumin
    0.46
    POSITIVE LOGITS
    نگی
    0.51
    انيا
    0.50
    ستخدم
    0.50
    хия
    0.47
    انات
    0.46
    开车
    0.46
     CFL
    0.46
    ция
    0.46
    كرة
    0.46
     slimy
    0.45
    Activations Density 0.001%

    No Known Activations