© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 41218
    Prev
    Next
    INDEX
    Explanations

    way followed by intensifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ı
    1.56
    みると
    1.55
    ä
    1.48
    ์
    1.48
    ्वती
    1.42
     pleasures
    1.41
     plight
    1.41
    ன
    1.41
    مان
    1.39
     было
    1.38
    POSITIVE LOGITS
    জ
    1.52
    dır
    1.39
    Y
    1.38
    P
    1.34
    くちゃ
    1.30
    ي
    1.27
    D
    1.26
    Z
    1.26
    H
    1.21
    З
    1.21
    Activations Density 0.000%

    No Known Activations