© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32660
    Prev
    Next
    INDEX
    Explanations

    except in

    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
    Transpose
    -0.73
     Clan
    -0.70
    اص
    -0.69
     corals
    -0.68
    Sensor
    -0.66
    wią
    -0.65
     SENSOR
    -0.65
    Yemen
    -0.65
    sensors
    -0.65
    underline
    -0.65
    POSITIVE LOGITS
    Arturo
    0.71
    Vidéo
    0.70
     idealized
    0.68
     spal
    0.68
     estrange
    0.67
    ôi
    0.67
    sweep
    0.66
    Perf
    0.66
    implicitly
    0.66
    סה
    0.65
    Activations Density 0.063%

    No Known Activations