© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 2696
    Prev
    Next
    INDEX
    Explanations

    contextual punctuation and separators

    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_65k_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
    akkhati
    2.59
    <unused67>
    2.43
     क़ुर्आन
    2.40
    <unused71>
    2.39
    Radiux
    2.37
    <unused56>
    2.37
    ुर्आन
    2.36
     Pusenk
    2.36
    asaddo
    2.36
    <unused864>
    2.36
    POSITIVE LOGITS
    The
    2.73
    For
    2.37
     The
    2.31
    To
    2.27
    In
    2.24
    An
    2.23
    With
    2.08
    From
    2.06
    On
    2.05
    It
    2.04
    Activations Density 1.347%

    No Known Activations