© 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. 13368
    Prev
    Next
    INDEX
    Explanations

    'The' or 'This' followed by a specific topic

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

    introduces content aspects or settings

    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
     svog
    0.43
     ponctué
    0.42
     شناس
    0.42
     منتقل
    0.41
     কর্মকাণ্ড
    0.40
     অ্যান্ড
    0.39
    .~\
    0.39
     endogenous
    0.39
     rencontr
    0.39
    errorhandler
    0.38
    POSITIVE LOGITS
     גם
    0.46
    ार्‍या
    0.43
     때문에
    0.42
     있으며
    0.41
     디자인
    0.41
     ні
    0.41
    ra
    0.40
    proteins
    0.40
     巴
    0.40
    ྲ
    0.40
    Activations Density 0.000%

    No Known Activations