© 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. 9862
    Prev
    Next
    INDEX
    Explanations

    funded by

    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
    I
    0.45
    A
    0.39
     I
    0.34
    r
    0.33
     A
    0.33
    f
    0.32
    l
    0.32
    v
    0.32
    If
    0.31
    O
    0.31
    POSITIVE LOGITS
     جائے۔
    0.30
    нуть
    0.28
    ripcion
    0.28
    ផ្សេង
    0.28
     και
    0.27
     spôsob
    0.27
    currentNode
    0.27
    도
    0.27
     biskup
    0.27
    𒊩
    0.27
    Activations Density 0.009%

    No Known Activations