© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2333
    Prev
    Next
    INDEX
    Explanations

    mimicking styles and patterns

    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
    Με
    2.85
    Ps
    2.58
    Π
    2.53
    ⁄
    2.37
    \]
    2.27
    \|
    2.26
     laurea
    2.23
    multicolumn
    2.23
    scribe
    2.15
    Ѓ
    2.11
    POSITIVE LOGITS
    ‌شده
    2.79
    paredStatement
    2.64
    agements
    2.63
    itated
    2.60
    कर्ता
    2.58
    ्ता
    2.55
    流域
    2.50
    ل
    2.49
    н
    2.46
    رین
    2.45
    Activations Density 0.037%

    No Known Activations