© 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. 53-GEMMASCOPE-2-RES-262K
    7. 66484
    Prev
    Next
    INDEX
    Explanations

    gradient change in direction

    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_53_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
    団
    0.39
     দিনাজ
    0.38
    locatorType
    0.38
    ীভূত
    0.37
    pile
    0.36
    脲
    0.36
    ერთ
    0.36
    團
    0.36
    〠
    0.36
    utional
    0.36
    POSITIVE LOGITS
     descent
    2.95
     descend
    2.77
     Descent
    2.72
     descended
    2.66
     descending
    2.64
     descends
    2.56
     ascent
    2.42
     Desc
    2.33
     ascend
    2.31
     ascending
    2.23
    Activations Density 0.052%

    No Known Activations