© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24480
    Prev
    Next
    INDEX
    Explanations

    article followed by title word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     молеку
    0.48
     типу
    0.45
    境界層
    0.41
     повинні
    0.41
     Entretanto
    0.41
    Bub
    0.40
     Prozess
    0.40
    ܤ
    0.40
    проце
    0.40
     должны
    0.40
    POSITIVE LOGITS
    il
    0.42
    ay
    0.41
    ig
    0.40
    ly
    0.39
    ida
    0.39
    le
    0.38
    lt
    0.38
    kg
    0.38
    api
    0.37
    ed
    0.37
    Activations Density 0.001%

    No Known Activations