© 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. 101414
    Prev
    Next
    INDEX
    Explanations

    categories and specific items

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

    financial and betting terms

    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
    katore
    0.50
     kth
    0.47
     Jh
    0.45
     mouse
    0.42
     kan
    0.42
    杮
    0.42
    狀態
    0.42
    កំណត់
    0.41
    ER
    0.41
     "?"]
    0.41
    POSITIVE LOGITS
     edificios
    0.55
     certificado
    0.52
    zos
    0.49
    ﺰ
    0.48
    ریت
    0.47
     atmosph
    0.46
     catégories
    0.46
    television
    0.46
    从未
    0.45
     categorías
    0.45
    Activations Density 0.000%

    No Known Activations