© 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. 203483
    Prev
    Next
    INDEX
    Explanations

    many options

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

    classifications and scope

    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
    紓
    0.47
    Seminar
    0.44
    Boo
    0.43
    Су
    0.42
    Uno
    0.42
    Tomas
    0.42
    London
    0.42
    didn
    0.42
    所有人
    0.41
    㬹
    0.41
    POSITIVE LOGITS
     Stef
    0.46
     Yin
    0.45
     táo
    0.45
     UFO
    0.44
     Deere
    0.44
     heirloom
    0.44
     Morin
    0.44
     Mooney
    0.44
     grantee
    0.43
     eğer
    0.43
    Activations Density 0.000%

    No Known Activations