© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9399
    Prev
    Next
    INDEX
    Explanations

    `or` and `and` conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_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
     zelfs
    0.48
     addirittura
    0.48
    耋
    0.45
     bahkan
    0.44
     nawet
    0.43
    そもそも
    0.41
     sogar
    0.40
    <0x0C>
    0.38
     حتی
    0.38
    总之
    0.38
    POSITIVE LOGITS
    ，
    0.41
     four
    0.39
    だけの
    0.38
     તથા
    0.36
    idig
    0.36
    cipher
    0.36
     Sheppard
    0.36
    wwww
    0.35
    ([
    0.35
    ،
    0.35
    Activations Density 0.290%

    No Known Activations