© 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. 222254
    Prev
    Next
    INDEX
    Explanations

    cerebral effect, Samsung Galaxy, parallelogram midpoint

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

    bipedal robot

    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
    atown
    0.47
    タリア
    0.44
     Jody
    0.44
    літ
    0.43
     Pandya
    0.42
    름
    0.42
    コリ
    0.42
     Brice
    0.42
     Feeding
    0.42
    arono
    0.42
    POSITIVE LOGITS
     carry
    0.55
     llev
    0.51
    Align
    0.47
     financeiros
    0.45
     bearers
    0.44
    ួល
    0.44
     potens
    0.44
     बग
    0.43
     γνω
    0.43
    \}=\
    0.42
    Activations Density 0.001%

    No Known Activations