© 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. 87826
    Prev
    Next
    INDEX
    Explanations

    buying deal

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

    asking "about" "centuries" and "question"

    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
    Able
    0.48
    Ip
    0.46
    投资
    0.45
    Copy
    0.45
    IP
    0.44
     IP
    0.43
    兽
    0.43
    Investment
    0.42
    Shard
    0.42
    ​​​​
    0.42
    POSITIVE LOGITS
    usted
    0.52
    ණු
    0.50
     fuer
    0.48
     jaoks
    0.48
    urg
    0.48
    ujo
    0.47
     señora
    0.47
    ėl
    0.45
     ekki
    0.45
     nicht
    0.45
    Activations Density 0.000%

    No Known Activations