© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11844
    Prev
    Next
    INDEX
    Explanations

    evoke feelings or senses

    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_7_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
    ي
    3.16
    ്യ
    2.85
    «.
    2.77
    рона
    2.76
    cstr
    2.74
    ्तिक
    2.73
    ்த்த
    2.70
    يّ
    2.69
    ்த்து
    2.67
    ের
    2.64
    POSITIVE LOGITS
    ঙ্খ
    2.75
    торы
    2.71
    רות
    2.70
    ाने
    2.70
    拉克
    2.68
    ので
    2.65
     уж
    2.64
    ा
    2.61
    Bronnen
    2.61
    ר
    2.58
    Activations Density 0.021%

    No Known Activations