© 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-65K
    7. 27621
    Prev
    Next
    INDEX
    Explanations

    categorize, theses, multilingual

    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_65k_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
    🤭
    0.46
     Vgl
    0.46
    তনে
    0.45
     ResultSet
    0.44
    isierung
    0.44
     Mhm
    0.44
     Цуки
    0.44
    чком
    0.44
     Thurston
    0.44
    സിക
    0.43
    POSITIVE LOGITS
    へと
    0.46
    υτό
    0.46
     categorize
    0.43
     theses
    0.42
    无比
    0.42
    【
    0.41
    这些
    0.40
     brillante
    0.40
     seeming
    0.40
     வண்ண
    0.40
    Activations Density 0.009%

    No Known Activations