© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 7434
    Prev
    Next
    INDEX
    Explanations

    target object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
     accords
    0.78
     প্রত্যাখ্যান
    0.74
     hechas
    0.72
     feito
    0.70
    ওয়ায়
    0.68
    不成
    0.67
     hecha
    0.67
     勝
    0.65
    LLCATS
    0.65
     courants
    0.64
    POSITIVE LOGITS
     target
    1.62
    你要
    1.61
    対象
    1.47
    target
    1.40
     Target
    1.36
    要
    1.31
    Target
    1.29
    我们要
    1.29
     대상
    1.23
    我們要
    1.22
    Activations Density 0.815%

    No Known Activations