© 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. 1664
    Prev
    Next
    INDEX
    Explanations

    variables or expressions involving 'x'

    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
     hydropon
    1.07
     decadent
    1.05
     sarcastic
    1.04
     misog
    0.99
     dystopian
    0.98
    <unused2194>
    0.98
     volupt
    0.97
     sexy
    0.97
     grotesque
    0.96
     wartime
    0.95
    POSITIVE LOGITS
    M
    1.21
    P
    1.20
    t
    1.17
    k
    1.15
    x
    1.15
    R
    1.15
    u
    1.14
    p
    1.13
    f
    1.13
    a
    1.11
    Activations Density 0.156%

    No Known Activations