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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 6805
    Prev
    Next
    INDEX
    Explanations

    sports seasons and games

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

    sports team wins or loses

    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
     loosing
    0.62
     এইসব
    0.52
     মোঃ
    0.49
     फ़ोन
    0.47
    ళ్ళ
    0.47
     ছিলোনা
    0.47
     हज़ार
    0.45
    㳳
    0.45
    రుగు
    0.45
     शुरु
    0.44
    POSITIVE LOGITS
     postseason
    0.51
    centric
    0.48
     offseason
    0.47
     cornerback
    0.47
     shortstop
    0.46
    Saturday
    0.44
     preseason
    0.44
    äck
    0.43
    妩
    0.43
     unquestionably
    0.41
    Activations Density 0.242%

    No Known Activations