© 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
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-RES-262K
    4. 62342
    Prev
    Next
    INDEX
    Explanations

    spec.ts or stg

    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_all/layer_41_width_262k_l0_big
    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
     magma
    0.44
    foundland
    0.41
     division
    0.40
    division
    0.40
    墅
    0.38
     WAIT
    0.38
    жеб
    0.37
    ثار
    0.37
    ហ៊
    0.37
     DiCaprio
    0.37
    POSITIVE LOGITS
    Debug
    0.53
    Release
    0.47
     Stable
    0.46
    试
    0.46
    ทด
    0.46
    测试
    0.45
     Release
    0.44
     realizzazione
    0.43
     teste
    0.42
     Debug
    0.42
    Activations Density 0.000%

    No Known Activations