Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12516
    Prev
    Next
    INDEX
    Explanations

    code attribute assignment

    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_16k_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
     are
    0.52
    6
    0.45
    8
    0.45
     )
    0.44
     is
    0.42
     diversión
    0.42
    and
    0.40
     são
    0.40
    สี
    0.40
     स्टाइल
    0.39
    POSITIVE LOGITS
    玦
    0.51
    kan
    0.47
    Khokhlov
    0.46
    可能な
    0.46
    jete
    0.46
    表
    0.46
     titul
    0.45
    ᕼ
    0.45
    Π
    0.45
    AsyncTask
    0.44
    Activations Density 0.134%

    No Known Activations