© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48122
    Prev
    Next
    INDEX
    Explanations

    Toma / Tama / Ama / Bama

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Countdown
    -0.81
    Continent
    -0.78
     нашего
    -0.74
     smugglers
    -0.72
    لاین
    -0.72
    Osi
    -0.72
    AKT
    -0.71
    entibus
    -0.69
    实际
    -0.69
    mug
    -0.69
    POSITIVE LOGITS
    amentul
    0.82
    culos
    0.81
    猫咪
    0.75
    ष्य
    0.74
    catch
    0.73
    ኖ
    0.73
    °
    0.72
     Tasmania
    0.71
     careful
    0.71
    paña
    0.71
    Activations Density 0.032%

    No Known Activations