© 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. 197205
    Prev
    Next
    INDEX
    Explanations

    after punctuation

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

    cashback on purchases

    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
    東京
    0.46
     fez
    0.44
     sétimo
    0.43
    大阪
    0.42
    第
    0.41
    𝗦
    0.41
     sixth
    0.41
    Cincinnati
    0.41
     London
    0.40
     Bratislava
    0.40
    POSITIVE LOGITS
    띈
    0.49
    닼
    0.48
    ujesz
    0.46
    AndPassword
    0.45
     содержит
    0.45
    åller
    0.44
     உள்ளட
    0.44
    학과
    0.43
     एंटी
    0.43
     strives
    0.43
    Activations Density 0.001%

    No Known Activations