© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 5152
    Prev
    Next
    INDEX
    Explanations

    abstract filtering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     inclusion
    0.84
     Existence
    0.80
     Inclusion
    0.79
     Theres
    0.79
     репре
    0.78
     又
    0.77
     Providing
    0.76
     predominance
    0.74
     corro
    0.74
    萑
    0.74
    POSITIVE LOGITS
    Abstract
    1.26
     Abstract
    0.90
    abstract
    0.78
     abstract
    0.75
     Kimberly
    0.75
    냇
    0.73
     abstracts
    0.72
    ena
    0.71
    abs
    0.69
    atek
    0.67
    Activations Density 0.001%

    No Known Activations