© 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. 44678
    Prev
    Next
    INDEX
    Explanations

    technical papers and conferences

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

    earth, sino, why, answering

    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
    akum
    0.53
    bere
    0.51
    事务
    0.51
    ingredients
    0.51
    gå
    0.51
    怔
    0.50
    session
    0.49
    inka
    0.48
    ่า
    0.48
    ้ำ
    0.47
    POSITIVE LOGITS
     vomit
    0.53
     φ
    0.49
     steaks
    0.48
     ὁ
    0.48
     situated
    0.47
     προσ
    0.47
     ξ
    0.47
     θ
    0.47
     ∠
    0.47
     topi
    0.47
    Activations Density 0.000%

    No Known Activations