© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5957
    Prev
    Next
    INDEX
    Explanations

    scar and dim related words

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

    dimming and scarring

    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
    Negative Logits
     Katt
    0.38
     Urb
    0.38
    isieren
    0.37
    ତ୍
    0.37
    isierung
    0.37
     alg
    0.37
     Mycobacterium
    0.37
    বৃন্দ
    0.37
    仠
    0.37
     Brennan
    0.36
    POSITIVE LOGITS
    med
    0.82
    pled
    0.77
     tissue
    0.75
    ples
    0.75
    tissue
    0.71
    ming
    0.71
    Tissue
    0.69
     Tissue
    0.65
    MED
    0.62
    red
    0.57
    Activations Density 0.036%

    No Known Activations