© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111688
    Prev
    Next
    INDEX
    Explanations

    Axis & Allies

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

    religious beliefs and funds

    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_31_width_262k_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
    텍
    0.47
     Maryland
    0.46
    แยก
    0.45
     acciaio
    0.45
    숑
    0.45
    গার
    0.43
     tees
    0.43
    ቴክ
    0.43
    地點
    0.42
    콤
    0.42
    POSITIVE LOGITS
     longitudinally
    0.48
    idaknya
    0.45
    ulfanyl
    0.44
    potentially
    0.44
     circadian
    0.43
     paediatric
    0.43
     sebab
    0.41
    relatively
    0.41
    rients
    0.41
    terior
    0.41
    Activations Density 0.000%

    No Known Activations