© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 3017
    Prev
    Next
    INDEX
    Explanations

    conjunctions and contrasts

    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
    overall
    1.07
     inoltre
    0.98
     additionally
    0.97
    Additionally
    0.97
    :,
    0.95
    factors
    0.94
    however
    0.91
    acariy
    0.90
    :
    0.87
    abhavena
    0.87
    POSITIVE LOGITS
     And
    2.22
     But
    1.92
     Not
    1.80
     Và
    1.77
     That
    1.65
     Nhưng
    1.64
     Or
    1.57
     Maybe
    1.48
     Literally
    1.44
     Lots
    1.44
    Activations Density 0.318%

    No Known Activations