© 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. 32525
    Prev
    Next
    INDEX
    Explanations

    add to cart or wishlist

    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
     शामिल
    0.49
    </s>
    0.43
    l
    0.42
    </tbody>
    0.41
    Unh
    0.41
    ()))
    0.41
    々に
    0.41
     значений
    0.40
    a
    0.40
    ять
    0.40
    POSITIVE LOGITS
     crédit
    0.52
     reservation
    0.45
     RSVP
    0.45
     appliqu
    0.44
     proceedings
    0.44
     Deniz
    0.43
     loosen
    0.43
     SCE
    0.43
     lu
    0.43
     priority
    0.43
    Activations Density 0.002%

    No Known Activations