© 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. 62065
    Prev
    Next
    INDEX
    Explanations

    journal citations and page numbers

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

    Indonesian place names and politics

    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
     нацыяна
    0.46
    觫
    0.46
    驊
    0.46
    Hearing
    0.45
    Bankruptcy
    0.45
    Референ
    0.45
    வையை
    0.45
    Platforms
    0.45
    ICPSR
    0.45
     liberalization
    0.44
    POSITIVE LOGITS
     Kecamatan
    0.66
     yakni
    0.57
     Polres
    0.55
     kecamatan
    0.54
     Kabupaten
    0.53
     Rumah
    0.51
     DPRD
    0.51
     T
    0.50
     Temp
    0.48
     granit
    0.48
    Activations Density 0.010%

    No Known Activations