© 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. 1730
    Prev
    Next
    INDEX
    Explanations

    truth, experiment, travel, specific ranks

    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
    s
    2.18
    т
    2.14
    ي
    2.02
    л
    1.80
    e
    1.77
    t
    1.76
    ו
    1.75
    ੀ
    1.75
    ా
    1.71
    ا
    1.71
    POSITIVE LOGITS
    обходимо
    1.90
    которые
    1.76
    ногда
    1.75
    frast
    1.69
    hibition
    1.65
    withstanding
    1.46
    theless
    1.44
    phalt
    1.44
    ductory
    1.43
    quiry
    1.41
    Activations Density 0.712%

    No Known Activations