© 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. 199871
    Prev
    Next
    INDEX
    Explanations

    Portable conditioners for

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

    asking about thoughts

    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
    密码
    0.46
    畢業
    0.45
    其實
    0.45
    軲
    0.45
    뺑
    0.45
    iteit
    0.44
    偷偷
    0.44
    PageState
    0.44
    izzate
    0.43
    那麼
    0.43
    POSITIVE LOGITS
    uj
    0.51
    prior
    0.50
     uj
    0.50
     elated
    0.49
    Z
    0.48
    x
    0.48
    Br
    0.47
     mbr
    0.47
    j
    0.46
    in
    0.46
    Activations Density 0.000%

    No Known Activations