© 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-16K
    7. 12647
    Prev
    Next
    INDEX
    Explanations

    surname, unity, hospital, anxiety

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

    might have

    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_16k_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
    另外
    0.55
    慫
    0.53
    ﺘ
    0.49
    फ्ल
    0.49
    睏
    0.48
    因為
    0.47
    峇
    0.47
    防疫
    0.46
    ഹമ്മ
    0.46
    গতকাল
    0.46
    POSITIVE LOGITS
    issait
    0.54
     reprim
    0.48
     deserial
    0.46
     gem
    0.45
    ähl
    0.45
    gem
    0.43
    iment
    0.43
     giving
    0.43
    žem
    0.43
    блица
    0.43
    Activations Density 0.000%

    No Known Activations