© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2241
    Prev
    Next
    INDEX
    Explanations

    detailed, core, good, ready

    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
    ih
    1.49
    isdir
    1.40
    ow
    1.38
    ir
    1.36
    };
    1.31
    ipy
    1.29
    ual
    1.28
    ouc
    1.28
    icit
    1.24
    inho
    1.23
    POSITIVE LOGITS
     하지
    1.87
     专业
    1.84
     Improving
    1.73
     用
    1.70
     konsep
    1.68
     Engagement
    1.65
     까지
    1.64
     Β
    1.64
     一个
    1.63
     즉
    1.61
    Activations Density 0.396%

    No Known Activations