© 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. 225012
    Prev
    Next
    INDEX
    Explanations

    reading app

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

    ethical and sensitive topics

    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
     крупней
    0.53
    𝘭
    0.46
    었던
    0.46
    이었
    0.44
    émi
    0.44
    லான
    0.44
     这些
    0.43
    这些
    0.42
     великолеп
    0.42
    ешься
    0.42
    POSITIVE LOGITS
     frivol
    0.45
     تريد
    0.42
    rowave
    0.42
    ृत्य
    0.40
     vogliono
    0.39
    </tbody>
    0.39
     bitrate
    0.38
     wavelength
    0.38
    頰
    0.38
     nominated
    0.38
    Activations Density 0.001%

    No Known Activations