© 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. 6626
    Prev
    Next
    INDEX
    Explanations

    sp, SP beginnings

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

    specificity, specifies

    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
    が通販できます
    0.43
     специалист
    0.43
    缥
    0.42
     специали
    0.40
    spielen
    0.39
    sphinx
    0.38
    spirit
    0.38
     espaces
    0.38
     spirit
    0.38
     sparse
    0.38
    POSITIVE LOGITS
    acular
    0.54
     المثال
    0.48
     lingk
    0.46
    檩
    0.42
    idey
    0.41
    innaker
    0.41
    ওনা
    0.39
    ANEOUS
    0.39
    anyol
    0.39
    ্র
    0.38
    Activations Density 0.430%

    No Known Activations