© 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. 68391
    Prev
    Next
    INDEX
    Explanations

    Geology, lips, Ripples, see, said, contact

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

    template, C++, reduce, airport

    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
    i
    0.54
    el
    0.52
    in
    0.49
    aw
    0.49
    cepc
    0.49
    omic
    0.48
    is
    0.48
    use
    0.48
    uni
    0.47
     she
    0.47
    POSITIVE LOGITS
     substitutions
    0.51
    ConfigFiles
    0.46
    ังหว
    0.46
    𝐽
    0.45
     jours
    0.44
     موفق
    0.43
     nitrog
    0.43
     substit
    0.42
    ሱን
    0.42
    ِمض
    0.42
    Activations Density 0.000%

    No Known Activations