© 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. 15763
    Prev
    Next
    INDEX
    Explanations

    explain a detail

    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
    ّا
    2.14
    close
    2.08
     close
    2.08
     volna
    1.98
    기가
    1.97
    olulu
    1.97
     vgl
    1.91
    활
    1.91
     ’
    1.88
     إنه
    1.88
    POSITIVE LOGITS
    anic
    2.70
    y
    2.70
    yto
    2.66
     MAKEINTRESOURCE
    2.54
    <{},
    2.48
    ClassLoader
    2.45
    XmlApplication
    2.42
     TestBed
    2.41
    yr
    2.40
    路径
    2.36
    Activations Density 0.040%

    No Known Activations