© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 3400
    Prev
    Next
    INDEX
    Explanations

    Russian/Slavic surnames and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     palab
    0.42
    IMUM
    0.42
    FERENCES
    0.42
    ইন্দ
    0.39
    abang
    0.39
    缦
    0.38
     coordenada
    0.38
     پیغم
    0.38
    陇
    0.38
    딪
    0.38
    POSITIVE LOGITS
    ovsky
    1.06
    kov
    1.05
    inski
    1.05
    ovsk
    1.05
    insky
    1.04
    insk
    1.02
    ovski
    1.01
    inskii
    0.99
    sky
    0.96
    ski
    0.96
    Activations Density 0.011%

    No Known Activations