© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2040
    Prev
    Next
    INDEX
    Explanations

    Russian names and place names

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

    names ending in "ina" or preceded by certain Russian syllables

    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
    
    0.41
    ScreenBinding
    0.41
    ælp
    0.41
    ാരം
    0.40
    Picking
    0.39
    蜞
    0.39
    상
    0.38
    WEIGHT
    0.38
    ilikom
    0.37
    
    0.37
    POSITIVE LOGITS
    ina
    0.80
    ină
    0.68
    ine
    0.67
    INA
    0.63
    িনা
    0.59
    ino
    0.58
    inas
    0.58
    тина
    0.57
    INE
    0.57
    rina
    0.56
    Activations Density 0.003%

    No Known Activations