© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6497
    Prev
    Next
    INDEX
    Explanations

    verb and expected word

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

    admire amazing

    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
    ԁ
    0.57
     ninety
    0.54
     https
    0.52
     thirteen
    0.50
     seventy
    0.48
     eighty
    0.48
     sixteen
    0.47
     ҡ
    0.47
     http
    0.47
    ҙ
    0.47
    POSITIVE LOGITS
    [`
    0.54
    `${
    0.52
    ```
    0.48
    ***
    0.47
    ``
    0.46
     [`
    0.44
    }`
    0.44
     `${
    0.44
     ```
    0.42
    ||
    0.40
    Activations Density 0.098%

    No Known Activations