© 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. 93580
    Prev
    Next
    INDEX
    Explanations

    joystick controls and Thrustmaster Logitech

    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
     pukul
    -0.68
     патро
    -0.68
     ai
    -0.66
    阿里
    -0.66
     Vicente
    -0.66
     computa
    -0.65
     nip
    -0.63
     Factors
    -0.63
     Snowden
    -0.63
     puncture
    -0.62
    POSITIVE LOGITS
     POV
    0.96
    POV
    0.95
     cockpit
    0.93
     rudder
    0.90
    erg
    0.87
     Thrust
    0.83
     Logitech
    0.82
    Thrust
    0.82
     pov
    0.82
     Leather
    0.81
    Activations Density 0.011%

    No Known Activations