© 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. 872
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     denotes
    0.84
    ᄑ
    0.80
     Wittgenstein
    0.78
    پ
    0.77
     ম
    0.77
    گ
    0.77
    ᆷ
    0.76
     ambiguity
    0.76
     ambiguous
    0.76
    큽
    0.76
    POSITIVE LOGITS
    並且
    1.20
     sehingga
    1.16
     ώστε
    1.14
     καθώς
    1.13
    並
    1.11
     вследствие
    1.09
    以及
    1.05
    并
    1.04
    并在
    1.03
     посредством
    1.01
    Activations Density 0.045%

    No Known Activations