© 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. 124337
    Prev
    Next
    INDEX
    Explanations

    travel, social media, or financial transactions

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

    Passport and visa requirements

    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
    met
    0.46
    mét
    0.45
    means
    0.45
    ني
    0.41
     “”
    0.40
    cias
    0.40
     طالب
    0.40
     ”
    0.40
    metals
    0.40
     مخ
    0.40
    POSITIVE LOGITS
    ኖ
    0.48
    Accel
    0.47
     pire
    0.47
    सिक
    0.46
    炤
    0.44
    ться
    0.44
     dinding
    0.44
     exaggerate
    0.44
    ').':
    0.43
     worsened
    0.43
    Activations Density 0.000%

    No Known Activations