© 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. 8011
    Prev
    Next
    INDEX
    Explanations

    cause harm or pain

    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
    дный
    2.75
     संदर्भ
    2.70
    oghi
    2.69
    ﺱ
    2.51
    rapped
    2.49
    д
    2.45
    iaj
    2.44
    ی
    2.36
     પડ
    2.35
     {*}
    2.34
    POSITIVE LOGITS
    c
    3.15
    ap
    2.61
    <bos>
    2.41
    p
    2.36
    f
    2.35
    mstyle
    2.32
    x
    2.24
    phor
    2.13
    ces
    2.10
    Ap
    2.06
    Activations Density 0.360%

    No Known Activations