© 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. 34857
    Prev
    Next
    INDEX
    Explanations

    definitively identified

    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
    u
    0.54
    ut
    0.51
    be
    0.51
    ul
    0.49
    g
    0.48
    lar
    0.47
    ð
    0.47
    uk
    0.47
    ühlen
    0.46
    ž
    0.46
    POSITIVE LOGITS
     pollute
    0.55
     douche
    0.50
     bandage
    0.48
     frowned
    0.45
     sniper
    0.45
     tuba
    0.44
     matériaux
    0.44
     tâches
    0.44
    了不少
    0.44
     bandages
    0.44
    Activations Density 0.002%

    No Known Activations