© 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
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 3285
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunction

    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
    нями
    0.76
    뭡
    0.74
    ുകയായിരുന്നു
    0.73
    ými
    0.71
     చేయడం
    0.71
     घेतल्या
    0.71
    чнее
    0.70
    lles
    0.68
    ními
    0.66
    ക്കുക
    0.65
    POSITIVE LOGITS
     but
    6.79
    but
    6.18
     nhưng
    5.64
     pero
    5.63
    但
    5.61
    But
    5.53
     But
    5.48
     ولكن
    5.19
     BUT
    5.17
     लेकिन
    5.12
    Activations Density 2.206%

    No Known Activations