© 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. 17932
    Prev
    Next
    INDEX
    Explanations

    as well as

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

    as of date

    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
    作為
    0.49
    作为
    0.48
    作为一个
    0.46
    としては
    0.45
     作为
    0.43
     rougeâtre
    0.42
     مثل
    0.42
    餑
    0.42
    ليزية
    0.41
    それが
    0.40
    POSITIVE LOGITS
     attested
    0.52
     aswell
    0.51
     evidenced
    0.49
    are
    0.48
     confirmed
    0.48
     noted
    0.47
     revealed
    0.45
     recorded
    0.44
     denoted
    0.44
     Taft
    0.44
    Activations Density 0.058%

    No Known Activations