© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71252
    Prev
    Next
    INDEX
    Explanations

    possible worlds, virtual worlds

    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
    <unused657>
    0.57
     samano
    0.54
     використову
    0.52
     બનાવે
    0.52
     vucc
    0.52
     tilapia
    0.50
    <unused437>
    0.50
     Сасик
    0.50
    <unused471>
    0.50
    <unused564>
    0.50
    POSITIVE LOGITS
     cyber
    0.45
     rider
    0.44
    runner
    0.42
    ing
    0.41
     world
    0.41
    supplier
    0.41
    stmt
    0.40
     hallar
    0.40
     first
    0.39
    企
    0.39
    Activations Density 0.000%

    No Known Activations