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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2249
    Prev
    Next
    INDEX
    Explanations

    authorization

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

    caller website

    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
    ąg
    0.41
    üşt
    0.37
    ă
    0.37
    แมนเชสเตอร์ซิตี
    0.37
    żli
    0.36
    っぷ
    0.36
    ąż
    0.36
    Ｘ
    0.36
    acją
    0.36
    缡
    0.36
    POSITIVE LOGITS
     horm
    0.41
     gly
    0.40
     lont
    0.39
     dator
    0.38
     satisf
    0.38
     dans
    0.38
     marav
    0.38
     emper
    0.38
     nim
    0.38
     olen
    0.37
    Activations Density 0.104%

    No Known Activations