© 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. 133673
    Prev
    Next
    INDEX
    Explanations

    )d

    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
    ലെസ്
    0.46
    録
    0.44
    录
    0.43
    Eggs
    0.43
     rivets
    0.42
     rivet
    0.42
    ሠ
    0.41
    Ỳ
    0.41
    Forgery
    0.41
    Personendaten
    0.41
    POSITIVE LOGITS
     Magic
    0.47
     multi
    0.46
     Re
    0.45
     Moz
    0.44
     BR
    0.43
     Multi
    0.42
    ecto
    0.41
     Multiple
    0.40
     multis
    0.40
     Oct
    0.40
    Activations Density 0.000%

    No Known Activations