© 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. 31-GEMMASCOPE-2-RES-262K
    7. 10004
    Prev
    Next
    INDEX
    Explanations

    acquisition and integration

    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
    मैंने
    0.47
     использу
    0.46
    த்தை
    0.46
     तभी
    0.44
     преподава
    0.44
    䐂
    0.44
     використову
    0.43
    学者
    0.43
    洴
    0.43
     दंप
    0.43
    POSITIVE LOGITS
     Unlike
    0.43
     a
    0.43
     refuse
    0.43
     apparel
    0.42
     stormwater
    0.42
     Fortnite
    0.42
     Snapdragon
    0.42
     recent
    0.41
     aggressive
    0.41
     from
    0.41
    Activations Density 0.002%

    No Known Activations