© 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. 218597
    Prev
    Next
    INDEX
    Explanations

    start of sentence fragments

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

    for beginners

    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
    DEL
    0.44
    }^*
    0.43
    食
    0.43
    Flag
    0.41
    amacare
    0.41
    FOOD
    0.41
    FLAGS
    0.40
    PACK
    0.39
     FOOD
    0.39
    𝐀
    0.39
    POSITIVE LOGITS
     Quaker
    0.54
     Eton
    0.52
     Ayrıca
    0.52
     роли
    0.50
     описа
    0.50
    凝聚
    0.50
     description
    0.49
     artı
    0.49
     repudi
    0.48
    వరకు
    0.48
    Activations Density 0.000%

    No Known Activations