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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 2765
    Prev
    Next
    INDEX
    Explanations

    concepts and definitions

    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
    ۔
    0.28
    》。
    0.21
     $)$.
    0.21
    。
    0.21
    ።
    0.21
    ).
    0.20
    '.
    0.19
    >.
    0.18
     ).
    0.18
    }.
    0.18
    POSITIVE LOGITS
     is
    0.28
     may
    0.25
     isn
    0.24
     seems
    0.24
     requires
    0.23
     είναι
    0.23
     diminishes
    0.23
     adds
    0.22
     gives
    0.22
     varies
    0.21
    Activations Density 0.507%

    No Known Activations