© 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. 791
    Prev
    Next
    INDEX
    Explanations

    key presses

    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
    MPC
    -0.81
    vē
    -0.77
     仮面
    -0.77
    Symbolic
    -0.75
     tpl
    -0.75
    HMIS
    -0.74
    TPL
    -0.74
    tsv
    -0.74
     Versa
    -0.73
     attirer
    -0.73
    POSITIVE LOGITS
     space
    2.41
    Space
    2.06
     SPACE
    2.00
    SPACE
    1.99
     Space
    1.99
    space
    1.98
    スペース
    1.49
    空间
    1.48
     espacio
    1.42
     espaço
    1.40
    Activations Density 0.017%

    No Known Activations