© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3464
    Prev
    Next
    INDEX
    Explanations

    areas for improvement or discussion

    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_7_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
    د
    3.49
    ும்ப
    2.88
    lado
    2.86
    ions
    2.85
    ᵏ
    2.73
     العربي
    2.70
    д
    2.68
    ᶦ
    2.61
     preload
    2.58
    ূলে
    2.58
    POSITIVE LOGITS
    \|
    2.68
    \]
    2.58
    $>$
    2.54
     وسهلا
    2.52
    sembl
    2.51
     ara
    2.37
    hus
    2.35
    맞
    2.35
    rahman
    2.29
    ἴ
    2.29
    Activations Density 0.069%

    No Known Activations