© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 70227
    Prev
    Next
    INDEX
    Explanations

    contributed to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
     to
    1.82
     or
    1.81
    or
    1.72
     naar
    1.70
    oport
    1.70
     so
    1.69
     and
    1.67
    ?
    1.66
     apropri
    1.65
    区分
    1.62
    POSITIVE LOGITS
    Furthermore
    1.84
     exacerbated
    1.80
     excès
    1.79
    Insufficient
    1.75
     sécher
    1.70
    Meanwhile
    1.65
    Consequently
    1.63
    Additionally
    1.62
     Expressway
    1.60
     loosened
    1.59
    Activations Density 0.005%

    No Known Activations