© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7305
    Prev
    Next
    INDEX
    Explanations

    California specific entities and laws

    np_acts-logits-general · gemini-2.5-flash-lite

    California consumer privacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ليز
    0.45
    ത്തില
    0.42
     shootings
    0.42
    жеб
    0.41
     nummer
    0.41
     σύν
    0.41
    လေ
    0.41
    葯
    0.40
     lớ
    0.39
     मैट्रिक्स
    0.39
    POSITIVE LOGITS
    variant
    0.44
     Alternate
    0.44
    EP
    0.39
     EP
    0.39
     Variation
    0.38
     Pendidikan
    0.38
     एपी
    0.38
     History
    0.37
    variation
    0.37
    Variant
    0.37
    Activations Density 0.001%

    No Known Activations