© 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. 1933
    Prev
    Next
    INDEX
    Explanations

    lawsuits

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

    numbers and quantities

    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
     zwölf
    0.15
     ahuv
    0.15
     ongeveer
    0.14
     soltanto
    0.14
     puluh
    0.14
    瓄
    0.13
     LOCCTR
    0.13
     largura
    0.13
    <unused1876>
    0.13
     posticis
    0.13
    POSITIVE LOGITS
    “
    0.13
     “
    0.12
    ies
    0.12
    ist
    0.12
     Great
    0.12
     famously
    0.11
     laws
    0.11
    <0xC2>
    0.11
    ings
    0.11
    ie
    0.11
    Activations Density 0.557%

    No Known Activations