© 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. 81
    Prev
    Next
    INDEX
    Explanations

    break

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

    break down

    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
    ሑ
    0.36
     لیتے
    0.35
     സഞ്ച
    0.34
     thiện
    0.34
    विष्ट
    0.34
    剿
    0.34
    งิน
    0.33
     두고
    0.33
    ዒ
    0.32
    ogonad
    0.31
    POSITIVE LOGITS
     break
    4.41
     Break
    4.28
    Break
    4.19
    break
    4.13
     BREAK
    4.09
     breaks
    4.06
     breaking
    4.03
    BREAK
    3.83
     Breaking
    3.81
     Breaks
    3.78
    Activations Density 0.389%

    No Known Activations