© 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. 26035
    Prev
    Next
    INDEX
    Explanations

    cricket test England

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

    fire starting material

    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
    mitt
    0.47
    reda
    0.46
    àm
    0.45
    olid
    0.44
    n
    0.43
    matt
    0.42
    à
    0.42
    oa
    0.42
     marc
    0.41
    serialize
    0.41
    POSITIVE LOGITS
     কাশ্ম
    0.42
     తాజాగా
    0.42
    扨
    0.42
     demanding
    0.41
    हर
    0.41
    ดังกล่าว
    0.41
     snowing
    0.40
     উক্ত
    0.40
    बॉलीवुड
    0.39
     बदले
    0.38
    Activations Density 0.001%

    No Known Activations