© 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. 115449
    Prev
    Next
    INDEX
    Explanations

    father who

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

    careful experiment and judgment

    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
    EL
    0.44
    恝
    0.44
     collaborator
    0.43
    IEF
    0.43
     foreigner
    0.42
    콧
    0.42
    ाइन
    0.41
     husband
    0.40
    INES
    0.40
     nationality
    0.40
    POSITIVE LOGITS
     اُ
    0.54
    lerden
    0.48
     پ
    0.46
     यही
    0.45
     pă
    0.45
    พ
    0.45
    ได้
    0.45
     необходимые
    0.44
    aları
    0.44
    はもちろん
    0.44
    Activations Density 0.001%

    No Known Activations