© 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. 9603
    Prev
    Next
    INDEX
    Explanations

    viewing, portals, prior, car, December

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

    opinion between

    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
    summar
    0.35
     दिसून
    0.32
     repre
    0.31
     تجزی
    0.30
    徇
    0.30
     evidences
    0.30
    譴
    0.29
    ുവരി
    0.29
     surm
    0.29
     multidiscipl
    0.29
    POSITIVE LOGITS
    um
    0.38
    iz
    0.36
     smoothies
    0.36
     cerveza
    0.36
    ix
    0.35
    ®,
    0.35
    ™
    0.35
    ®
    0.34
     and
    0.34
     panties
    0.33
    Activations Density 0.000%

    No Known Activations