© 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. 5958
    Prev
    Next
    INDEX
    Explanations

    red followed by flags, collar, or hot

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

    red flags

    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
    opathic
    0.40
    یسر
    0.40
    ⥤
    0.36
     NHE
    0.36
    peu
    0.36
     //-->
    0.35
     dismin
    0.35
     seniority
    0.35
    齬
    0.35
    getC
    0.35
    POSITIVE LOGITS
    色的
    1.02
    shirt
    0.94
    shirts
    0.88
    oubt
    0.84
    色の
    0.82
     haired
    0.81
    coats
    0.79
    haired
    0.79
     shirt
    0.78
     collar
    0.78
    Activations Density 0.105%

    No Known Activations