© 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. 10410
    Prev
    Next
    INDEX
    Explanations

    seek help, support, or opportunities

    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
    t
    2.24
    tions
    2.23
    醐
    2.12
    মরা
    2.03
    dır
    2.03
     badan
    2.02
    ributedString
    1.96
    tog
    1.94
    nc
    1.93
    ا
    1.92
    POSITIVE LOGITS
     BeautifulSoup
    2.41
    た
    2.36
    答え
    2.24
     gonflement
    2.22
    ♝
    2.19
     indulgent
    2.18
    撳
    2.18
    不及
    2.17
    année
    2.16
    כו
    2.16
    Activations Density 0.189%

    No Known Activations