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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 125165
    Prev
    Next
    INDEX
    Explanations

    after certain words

    np_acts-logits-general · gemini-2.5-flash-lite

    series, sequence, iterator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stri
    0.54
    kst
    0.49
    kta
    0.48
    k
    0.48
    ransition
    0.47
    า
    0.47
    irar
    0.47
    ⑸
    0.47
    ках
    0.47
     сво
    0.45
    POSITIVE LOGITS
     Q
    0.49
     Ř
    0.49
     Beide
    0.49
     S
    0.48
     genug
    0.46
     B
    0.46
     Purple
    0.46
     blijven
    0.45
     Delt
    0.45
     Sunglasses
    0.45
    Activations Density 0.001%

    No Known Activations