© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 104263
    Prev
    Next
    INDEX
    Explanations

    vanagons, Forest, España, modeling, Pie, iPhone

    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_16_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
     compatriots
    0.68
    ’
    0.67
    ,»
    0.62
     repercussions
    0.61
    今年は
    0.61
    લ
    0.58
    ,”
    0.57
     commendable
    0.57
     grandpa
    0.57
    ”
    0.57
    POSITIVE LOGITS
    ام
    0.71
    ח
    0.65
    ان
    0.64
    mimpi
    0.61
    مل
    0.57
    ه
    0.57
     objets
    0.55
    ما
    0.55
     Artifact
    0.55
    ่
    0.55
    Activations Density 0.000%

    No Known Activations