© 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. 120446
    Prev
    Next
    INDEX
    Explanations

    counting items in text

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

    numbers, language, paper, bonds

    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
    K
    0.52
     angezeigt
    0.49
     воздей
    0.48
    unpublished
    0.46
     شک
    0.46
     jednego
    0.46
     питань
    0.46
    өрд
    0.46
    훔
    0.46
    Prz
    0.46
    POSITIVE LOGITS
    个数
    0.49
     counts
    0.47
     catchment
    0.46
    slotBox
    0.46
    రాలు
    0.45
     entrees
    0.45
    ఎల్
    0.45
     landscape
    0.44
     larch
    0.44
    粨
    0.44
    Activations Density 0.001%

    No Known Activations