© 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. 124685
    Prev
    Next
    INDEX
    Explanations

    reading or mentioning books

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

    country identification and inspiration

    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
    <0x0D>
    0.55
     at
    0.48
    </i>
    0.46
    LL
    0.43
     constitu
    0.43
    \
    0.41
     商品
    0.41
    0.41
    conn
    0.40
    </b>
    0.39
    POSITIVE LOGITS
    irrahim
    0.50
     ఏర్
    0.49
    嵬
    0.44
     ഇന്ന്
    0.44
     eagerly
    0.43
    வர்களை
    0.43
     skiers
    0.43
    ivasena
    0.43
     bowlers
    0.43
    蒉
    0.42
    Activations Density 0.001%

    No Known Activations