© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81745
    Prev
    Next
    INDEX
    Explanations

    less common or efficient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ە
    0.67
    the
    0.63
     attendants
    0.63
     minimizes
    0.62
    ت
    0.61
    ه
    0.61
    ties
    0.61
    these
    0.61
    ב
    0.60
     citations
    0.60
    POSITIVE LOGITS
     less
    0.70
     favorita
    0.62
    с
    0.60
     spectacularly
    0.59
     خير
    0.58
     ساي
    0.58
    Less
    0.57
     financi
    0.57
    eless
    0.57
     менее
    0.56
    Activations Density 0.041%

    No Known Activations