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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 9262
    Prev
    Next
    INDEX
    Explanations

    private class members

    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
     bear
    1.00
     including
    0.97
     saying
    0.96
     whether
    0.93
     ‘
    0.92
     even
    0.92
     nay
    0.92
     worthy
    0.91
     watch
    0.89
     definitely
    0.89
    POSITIVE LOGITS
    iftoire
    1.70
    Ᏻ
    1.68
    Arqu
    1.62
    ="#!"
    1.53
    Тре
    1.53
     Química
    1.50
    Ꭻ
    1.50
    Ꮸ
    1.50
    <unused252>
    1.49
     जेईई
    1.49
    Activations Density 0.002%

    No Known Activations