© 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. 77098
    Prev
    Next
    INDEX
    Explanations

    words indicating processes or states

    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
    འི་
    0.42
     humanitarian
    0.41
    新的
    0.40
     V
    0.39
     particularly
    0.38
    那個
    0.38
     }^{
    0.37
     Particularly
    0.37
     philanthropic
    0.37
     voda
    0.37
    POSITIVE LOGITS
    幵
    0.52
     możesz
    0.50
     يمكنك
    0.45
    ुन
    0.45
    Placement
    0.44
     podrás
    0.44
     нач
    0.43
    骡
    0.43
     можете
    0.43
     самостоя
    0.43
    Activations Density 0.016%

    No Known Activations