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. 12244
    Prev
    Next
    INDEX
    Explanations

    * ( ) $

    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
    Also
    0.46
    Certain
    0.44
    所得
    0.43
    Error
    0.43
    名を
    0.42
     derivatives
    0.40
     Variations
    0.40
    V
    0.40
     Certain
    0.39
     Polynomial
    0.39
    POSITIVE LOGITS
    ടിക്ക
    0.47
    ्रेडिट
    0.44
    滋
    0.44
     pushedAt
    0.40
     diber
    0.40
    DetailsService
    0.39
     Tjiwarl
    0.39
     ততদিন
    0.39
    ışt
    0.38
    manha
    0.38
    Activations Density 0.246%

    No Known Activations