© 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. 211170
    Prev
    Next
    INDEX
    Explanations

    help and numbers

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

    spills immediately

    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
    ंता
    0.47
    ﺒ
    0.46
    ുപത്രി
    0.46
    दिग्ध
    0.45
    ۷
    0.45
    芏
    0.45
    Ｐ
    0.44
    стная
    0.43
    Ц
    0.43
    Ст
    0.43
    POSITIVE LOGITS
    ảo
    0.51
    '
    0.50
    rika
    0.49
     casework
    0.48
     kiểm
    0.48
     கண
    0.46
     editors
    0.45
    ork
    0.45
     guesswork
    0.44
    </h2>
    0.44
    Activations Density 0.000%

    No Known Activations