© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 4882
    Prev
    Next
    INDEX
    Explanations

    conditional phrasing

    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_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
     ha
    0.88
     homes
    0.86
     h
    0.85
    ,
    0.83
     continu
    0.83
     likes
    0.82
     aspect
    0.82
     loves
    0.82
     first
    0.80
     off
    0.78
    POSITIVE LOGITS
    ##
    1.53
    If
    1.51
    ###
    1.50
    Если
    1.47
    However
    1.47
    <h3>
    1.45
    Jeśli
    1.43
    Interestingly
    1.43
    Despite
    1.43
    <h2>
    1.43
    Activations Density 0.602%

    No Known Activations