© 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. 29-GEMMASCOPE-2-RES-65K
    7. 2786
    Prev
    Next
    INDEX
    Explanations

    what is needed

    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_29_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
    ਠ
    0.68
    𝙼
    0.66
    wiąz
    0.63
    ֩
    0.63
     ತಪ್ಪ
    0.62
    โทษ
    0.61
    颇
    0.61
    恭
    0.61
    ულია
    0.60
     marad
    0.60
    POSITIVE LOGITS
     need
    5.35
     needs
    5.29
     Needs
    4.74
    need
    4.72
    needs
    4.72
     Need
    4.71
    需要
    4.56
    Need
    4.54
    Needs
    4.45
     necessidade
    4.45
    Activations Density 2.128%

    No Known Activations