© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4107
    Prev
    Next
    INDEX
    Explanations

    passing, passed, passage

    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
    ĝ
    0.65
    ρθρο
    0.64
    ито
    0.63
    ফিক
    0.63
     ज्वाइन
    0.62
    واعد
    0.61
     본격
    0.61
     méthodique
    0.61
    ))+\
    0.60
    rinos
    0.57
    POSITIVE LOGITS
     pass
    5.02
     passing
    4.96
    Pass
    4.89
     Pass
    4.76
     passes
    4.73
     passed
    4.70
    Passing
    4.64
     Passing
    4.64
    pass
    4.62
    passing
    4.50
    Activations Density 0.586%

    No Known Activations