© 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. 96483
    Prev
    Next
    INDEX
    Explanations

    News

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

    news-room and press releases

    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
    다
    0.52
    𝟭
    0.50
    ه‌ها
    0.49
    Integrante
    0.49
    democracy
    0.46
    یل
    0.44
    굿
    0.44
    اً
    0.43
    ه‌های
    0.43
    elt
    0.42
    POSITIVE LOGITS
     conjuntos
    0.49
     produ
    0.48
     bure
    0.47
     horm
    0.45
     lumea
    0.45
    ൂ
    0.45
     newsp
    0.42
     poner
    0.42
     nort
    0.42
     tine
    0.42
    Activations Density 0.005%

    No Known Activations