© 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. 244305
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    撐
    0.44
    Tambah
    0.43
    add
    0.40
    Add
    0.39
    齬
    0.39
    cho
    0.38
    boost
    0.38
    ോളം
    0.38
    淐
    0.38
    Diverse
    0.38
    POSITIVE LOGITS
     captures
    0.45
     killing
    0.44
     intercepts
    0.44
     trapping
    0.43
     verbs
    0.43
     figurines
    0.43
     flowering
    0.43
     typeface
    0.43
     capture
    0.42
     preventing
    0.42
    Activations Density 0.004%

    No Known Activations