© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 47769
    Prev
    Next
    INDEX
    Explanations

    related to objects, people, products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    㴌
    0.41
    สัตว์
    0.40
    ன்களை
    0.39
    linkCell
    0.39
    ങ്ങളില്‍
    0.39
    FIC
    0.38
    WITT
    0.38
     точке
    0.38
    ଐ
    0.38
     යු
    0.37
    POSITIVE LOGITS
     alongside
    0.43
     υπάρχ
    0.41
    s
    0.40
     scattered
    0.39
    करणा
    0.39
     with
    0.38
     helps
    0.38
    ównie
    0.37
    porcion
    0.37
     under
    0.37
    Activations Density 0.000%

    No Known Activations