© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10501
    Prev
    Next
    INDEX
    Explanations

    competence

    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
    老板
    1.87
    哌
    1.78
    ဳ
    1.73
     روب
    1.73
    لوان
    1.70
    老闆
    1.69
     جشنواره
    1.67
    𒄿
    1.65
    ជ្
    1.64
    tiket
    1.63
    POSITIVE LOGITS
    ings
    1.53
     fl
    1.14
    ("
    1.12
     ("
    1.10
     Fl
    1.09
    care
    1.07
    INGS
    1.06
    :
    1.06
     t
    1.05
     care
    1.04
    Activations Density 0.000%

    No Known Activations