© 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. 149269
    Prev
    Next
    INDEX
    Explanations

    shambling, school with, slash sheet, Sea Spa

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

    links and categories

    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
    )}")
    0.47
    tank
    0.46
    坪
    0.46
    collapsed
    0.45
    ten
    0.45
    ள்ளார்
    0.44
    tensor
    0.44
    ಳ್ಳ
    0.44
    covariance
    0.44
    enjoy
    0.43
    POSITIVE LOGITS
     who
    0.59
     Sev
    0.52
     serpent
    0.51
     Saba
    0.51
    oub
    0.50
     skute
    0.50
     E
    0.49
     quem
    0.48
     tigre
    0.48
     Mouth
    0.48
    Activations Density 0.000%

    No Known Activations