© 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. 1732
    Prev
    Next
    INDEX
    Explanations

    compression followed by punctuation

    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
    。
    3.08
    ।
    2.83
    .
    2.81
    .\\
    2.64
    .}
    2.64
    。(
    2.58
    }.
    2.58
    .";
    2.56
    .。
    2.55
    .\
    2.54
    POSITIVE LOGITS
     فإن
    0.95
    ?),
    0.95
    ֨
    0.85
     itulah
    0.84
    )?,
    0.82
     inilah
    0.79
     ),
    0.79
    ...),
    0.79
    怎么办
    0.76
     మాత్రం
    0.76
    Activations Density 1.162%

    No Known Activations