© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7723
    Prev
    Next
    INDEX
    Explanations

    learning from raw text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    5
    1.19
    6
    1.19
    2
    1.18
    4
    1.15
    1
    1.11
     gerektiğini
    1.08
     بیشتری
    1.07
     suficientes
    1.06
     Questo
    1.06
     Differ
    1.06
    POSITIVE LOGITS
     aptly
    1.51
    <em>
    1.48
    ⟨
    1.41
     titled
    1.37
    <strong>
    1.37
    heading
    1.34
    labelled
    1.32
    ᱛ
    1.31
     termed
    1.31
    ̱
    1.30
    Activations Density 0.027%

    No Known Activations