© 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. 202098
    Prev
    Next
    INDEX
    Explanations

    babies and grandchildren

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

    by default

    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
    滪
    0.58
    OnClickListener
    0.55
     बुन्देलखण्ड
    0.55
     окончания
    0.54
     فريبي
    0.52
    ertura
    0.52
     आल्सो
    0.50
    @@]
    0.50
     выпуска
    0.50
     кеңсесинде
    0.49
    POSITIVE LOGITS
     crystal
    0.53
     steril
    0.45
    0.45
     digit
    0.45
     mission
    0.44
    िशन
    0.44
     nez
    0.43
     cuyas
    0.43
     grandchild
    0.43
     scipy
    0.43
    Activations Density 0.000%

    No Known Activations