© 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. 5884
    Prev
    Next
    INDEX
    Explanations

    fixed actions or confirmation

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

    fixed or correcting

    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
    pani
    0.46
    ณฑ
    0.41
    唝
    0.41
     ARMY
    0.40
    पर
    0.40
    astri
    0.39
     PAN
    0.39
     ወ
    0.39
    พัน
    0.38
     TAG
    0.38
    POSITIVE LOGITS
     fixed
    0.63
    Fixed
    0.61
     Fixed
    0.59
    固定
    0.57
     固定
    0.57
    fixed
    0.56
     FIXED
    0.55
     smelt
    0.50
     smell
    0.49
     smells
    0.48
    Activations Density 0.000%

    No Known Activations