© 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. 1192
    Prev
    Next
    INDEX
    Explanations

    conjunctions and quantifiers

    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
     is
    0.64
     B
    0.47
     A
    0.46
    +:
    0.44
     Diels
    0.44
     Eiffel
    0.43
     was
    0.43
     N
    0.42
     C
    0.40
     নিলে
    0.40
    POSITIVE LOGITS
     (!)
    0.55
    (!)
    0.51
    ла
    0.49
    rdquo
    0.48
    ہ
    0.47
    㕝
    0.47
    sthe
    0.45
    "
    0.43
    ❞
    0.43
    𝗻
    0.43
    Activations Density 0.728%

    No Known Activations