© 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. 175218
    Prev
    Next
    INDEX
    Explanations

    restaurants, home, class, die, Billie, activities, counselor, Tuesday

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

    Scott Alexander essay references

    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
     Y
    0.49
     sadd
    0.47
     ۴
    0.46
     querido
    0.45
     Schulz
    0.45
    ત્મક
    0.45
     Anushka
    0.44
    7
    0.43
    оте
    0.43
     physical
    0.42
    POSITIVE LOGITS
     atomically
    0.51
    Timestamp
    0.50
     निकायों
    0.49
    社區
    0.48
    銠
    0.47
    deviceId
    0.45
    发布
    0.45
    accessToken
    0.45
    Người
    0.45
    持續
    0.44
    Activations Density 0.000%

    No Known Activations