© 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. 182806
    Prev
    Next
    INDEX
    Explanations

    **all**

    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
    ри
    0.42
    世界
    0.41
    rope
    0.40
    um
    0.39
     boundedness
    0.39
     wrestling
    0.39
    дин
    0.38
    檻
    0.38
    வு
    0.37
    ρό
    0.37
    POSITIVE LOGITS
     μπορεί
    0.45
     اکثر
    0.44
     możesz
    0.43
     Kamu
    0.42
     pouvez
    0.42
     posso
    0.42
     kannst
    0.41
     unités
    0.41
     mogę
    0.41
    StillWater
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.