© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 722
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings

    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
    ཎ
    0.88
     हज़ार
    0.82
    𝓢
    0.81
     LN
    0.79
     //-
    0.78
    UILLER
    0.77
     હજાર
    0.76
     الكسور
    0.76
    榃
    0.75
     Scientology
    0.75
    POSITIVE LOGITS
    bc
    1.16
    ae
    1.03
     b
    1.03
    b
    1.02
    df
    1.01
    bcc
    0.99
    cb
    0.99
    aac
    0.98
    bb
    0.98
     c
    0.97
    Activations Density 0.074%

    No Known Activations