© 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. 110820
    Prev
    Next
    INDEX
    Explanations

    counting two

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

    information, learning, resources

    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
    -
    0.95
    /
    0.66
    ‐
    0.59
    -/
    0.54
     and
    0.54
    ’-
    0.53
    ・
    0.53
     insurgency
    0.52
    ­
    0.52
     markets
    0.51
    POSITIVE LOGITS
    ungkinkan
    0.61
     δύο
    0.58
     deux
    0.58
     two
    0.57
     двумя
    0.57
    dır
    0.55
    मतौर
    0.55
    ittää
    0.55
     ሁለት
    0.54
    एक
    0.53
    Activations Density 0.001%

    No Known Activations