© 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. 40-GEMMASCOPE-2-RES-262K
    7. 7713
    Prev
    Next
    INDEX
    Explanations

    its'

    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_40_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
    cakes
    0.53
     ট্র
    0.49
    combined
    0.49
    нів
    0.48
    messe
    0.47
    Ŷ
    0.47
    γκε
    0.46
     auxqu
    0.46
    धि
    0.45
    ost
    0.45
    POSITIVE LOGITS
     argues
    0.45
     período
    0.45
     prism
    0.44
     argue
    0.43
     veget
    0.42
     Este
    0.42
    ഈ
    0.42
     near
    0.42
     timelines
    0.42
     any
    0.41
    Activations Density 0.000%

    No Known Activations