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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 56523
    Prev
    Next
    INDEX
    Explanations

    research paper titles

    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_65k_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
    ng
    0.43
    bing
    0.42
    <start_of_image>
    0.39
    in
    0.38
    }\
    0.37
    with
    0.37
     trail
    0.37
     performs
    0.37
     allergic
    0.36
    lte
    0.36
    POSITIVE LOGITS
     Tarifleri
    0.42
     Capítulo
    0.41
     dioses
    0.41
    峤
    0.40
    Archivo
    0.39
    хии
    0.39
    𝔂
    0.39
    导体
    0.38
    <0xDB>
    0.38
     मालिकों
    0.38
    Activations Density 0.003%

    No Known Activations