© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75304
    Prev
    Next
    INDEX
    Explanations

    full memory dump

    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
     água
    0.50
    اي
    0.49
    γράφ
    0.48
    标签
    0.47
     voda
    0.47
    ის
    0.47
    水
    0.47
     etiqueta
    0.46
    Imagem
    0.46
    тли
    0.46
    POSITIVE LOGITS
     reverence
    0.44
     unable
    0.43
     /
    0.42
     hemisph
    0.42
    urp
    0.41
    rom
    0.40
     cessation
    0.40
    rance
    0.40
     تنا
    0.39
    unable
    0.39
    Activations Density 0.000%

    No Known Activations