© 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. 201383
    Prev
    Next
    INDEX
    Explanations

    tile offers, daily flights, shop for

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

    protocols, solutions, or motion

    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
    ow
    0.48
    -
    0.45
    lan
    0.42
    ॉय
    0.41
    蓝牙
    0.39
    اب
    0.38
    ボ
    0.38
    ot
    0.38
    aw
    0.38
     devices
    0.38
    POSITIVE LOGITS
     Pyongyang
    0.52
     નક્કી
    0.50
     Rohing
    0.49
     அல்லது
    0.49
     cloro
    0.48
     Seine
    0.47
     Agios
    0.47
     mermaid
    0.46
     Diy
    0.46
     Sebasti
    0.46
    Activations Density 0.003%

    No Known Activations