© 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. 70641
    Prev
    Next
    INDEX
    Explanations

    multilingual or punctuation/formatting

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

    Critic, Nakamoto, crowdsourced, response

    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
     ball
    0.42
     orphaned
    0.41
     তবু
    0.41
     unable
    0.41
     נע
    0.40
     http
    0.40
     $.
    0.40
     cell
    0.40
     slowest
    0.39
     malaria
    0.39
    POSITIVE LOGITS
     يُ
    0.47
    といった
    0.46
     çeşitli
    0.44
    以及
    0.43
    それぞれ
    0.42
    出來
    0.42
     Comes
    0.42
     등의
    0.42
    <0x0B>
    0.41
     इंग
    0.41
    Activations Density 0.001%

    No Known Activations