© 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. 225694
    Prev
    Next
    INDEX
    Explanations

    damage or loss caused or

    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
    nsen
    0.45
    மாக
    0.44
    ␮
    0.44
     प्रसारित
    0.43
     menurun
    0.42
    lind
    0.42
     প্রেক্ষিতে
    0.42
     লেখ
    0.41
     metà
    0.40
     scrittura
    0.40
    POSITIVE LOGITS
    orientation
    0.46
    UEZ
    0.46
    Orientation
    0.44
     journey
    0.44
    派
    0.42
     LAND
    0.41
    ായ
    0.41
    다
    0.40
    ี้
    0.40
    journey
    0.40
    Activations Density 0.000%

    No Known Activations