© 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. 40-GEMMASCOPE-2-RES-262K
    7. 133841
    Prev
    Next
    INDEX
    Explanations

    index signatures or dictionary keys

    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_40_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
    壮
    0.42
     meng
    0.41
     objek
    0.40
     SMAD
    0.40
     Object
    0.39
    壯
    0.39
     oggetto
    0.39
     Harwell
    0.37
     sylvis
    0.37
     objeto
    0.37
    POSITIVE LOGITS
    ographer
    0.43
     Jahrze
    0.41
     ጥ
    0.41
     century
    0.40
    édié
    0.39
     sham
    0.38
    百年
    0.38
    碜
    0.38
    ierzchn
    0.37
     எண்ணெய்
    0.37
    Activations Density 0.001%

    No Known Activations