© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92920
    Prev
    Next
    INDEX
    Explanations

    Amiga joystick

    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
    コーチ
    -0.77
    Carolina
    -0.71
     Tait
    -0.71
     commented
    -0.70
     roślin
    -0.69
    ляется
    -0.69
    ветить
    -0.69
     Principe
    -0.68
     graduated
    -0.68
     positive
    -0.68
    POSITIVE LOGITS
    म्
    0.85
     KERN
    0.84
    Ultimate
    0.74
     disk
    0.74
    disk
    0.73
    neurons
    0.69
    raster
    0.68
     Belastung
    0.68
    Poke
    0.68
     IEEE
    0.68
    Activations Density 0.027%

    No Known Activations