© 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. 242165
    Prev
    Next
    INDEX
    Explanations

    PE ratio and delivery

    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
     tuvimos
    0.50
     klubu
    0.49
    র্জাতিক
    0.49
     গিয়েছিলাম
    0.49
     enero
    0.49
     hicimos
    0.46
     এসেছিল
    0.46
    <unused537>
    0.45
    <unused1072>
    0.45
     possiamo
    0.45
    POSITIVE LOGITS
    /
    0.50
    (-
    0.47
    Other
    0.46
     другими
    0.46
    其它
    0.46
     (
    0.45
     refor
    0.42
    獭
    0.42
    LA
    0.42
    -+
    0.41
    Activations Density 0.000%

    No Known Activations