© 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. 44546
    Prev
    Next
    INDEX
    Explanations

    particle filters

    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
     끊
    0.44
    прия
    0.44
     경기
    0.44
     मनोविज्ञान
    0.44
    diği
    0.44
     зако
    0.44
    ௐ
    0.42
    వ్య
    0.42
    萧
    0.42
    竞技
    0.42
    POSITIVE LOGITS
     they
    0.58
    م
    0.47
     museum
    0.46
     themselves
    0.46
     planes
    0.45
     their
    0.44
     name
    0.44
     thatched
    0.43
     people
    0.43
     m
    0.42
    Activations Density 0.006%

    No Known Activations