© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1992
    Prev
    Next
    INDEX
    Explanations

    un followed by discovery or unpredictability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     implicit
    0.63
     prow
    0.61
    a
    0.61
    捞
    0.60
     Table
    0.59
     inactive
    0.59
     table
    0.58
     ?>
    0.57
     inactivity
    0.56
    Table
    0.56
    POSITIVE LOGITS
    fortun
    1.13
    surprisingly
    1.05
    ipolar
    1.03
    paralleled
    1.02
    iqueness
    1.02
    fortunately
    1.01
    ilateral
    0.99
    ilever
    0.98
    bilical
    0.98
    brellas
    0.96
    Activations Density 0.092%

    No Known Activations