© 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. 1644
    Prev
    Next
    INDEX
    Explanations

    designed for a purpose

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

    tools for building solutions

    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
     yapılan
    0.46
    庥
    0.45
    പ്പെട്ടു
    0.43
     ምልክ
    0.41
     szok
    0.41
     etern
    0.39
     uncontroll
    0.39
    𝓇
    0.39
     querer
    0.39
    リューム
    0.38
    POSITIVE LOGITS
     capable
    1.45
     tailored
    1.39
     capaz
    1.30
     suitable
    1.29
     designed
    1.24
     aimed
    1.23
    capable
    1.22
     suited
    1.19
     geared
    1.19
     capazes
    1.16
    Activations Density 0.582%

    No Known Activations