© 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. 50993
    Prev
    Next
    INDEX
    Explanations

    automation, Withdraw, Heritage science

    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
    anceled
    0.46
    وَ
    0.46
    ilibr
    0.44
    it
    0.42
    primarily
    0.42
    England
    0.41
    ̀
    0.41
    both
    0.40
    सुन
    0.40
    cenie
    0.40
    POSITIVE LOGITS
    ால்
    0.46
     antif
    0.46
     coolers
    0.45
     ladders
    0.45
     اسلح
    0.43
     armas
    0.42
     образ
    0.41
     Begriff
    0.41
     armes
    0.41
    萺
    0.41
    Activations Density 0.000%

    No Known Activations