© 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. 34667
    Prev
    Next
    INDEX
    Explanations

    verbs of being

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

    are a

    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
    BURTS
    0.45
    URER
    0.43
    EPO
    0.40
    涂
    0.39
    锟
    0.39
    Dao
    0.39
     себе
    0.39
    ریب
    0.38
    Liver
    0.38
    Ģ
    0.38
    POSITIVE LOGITS
    laf
    0.45
     piped
    0.40
     nic
    0.39
     يصل
    0.38
    まで
    0.38
     delic
    0.38
     Nic
    0.38
     Objects
    0.37
     delicacy
    0.37
     Vt
    0.36
    Activations Density 0.000%

    No Known Activations