© 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. 18211
    Prev
    Next
    INDEX
    Explanations

    verbs and specific nouns

    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
     Wrangler
    0.57
    )$
    0.44
    renden
    0.44
    地に
    0.44
    Many
    0.43
    Daniel
    0.43
    mount
    0.43
     Ansible
    0.43
    Finish
    0.42
    éditeur
    0.41
    POSITIVE LOGITS
     ఎలా
    0.50
     scourge
    0.46
     використо
    0.46
     इसका
    0.45
    aturas
    0.44
    馆
    0.43
     እንዴት
    0.42
     deformation
    0.42
     conhecimentos
    0.42
     থাকলেও
    0.42
    Activations Density 0.001%

    No Known Activations