© 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. 1299
    Prev
    Next
    INDEX
    Explanations

    domain names

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

    instructions and explanations

    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
     ljub
    0.50
     Reservation
    0.47
    氹
    0.45
     তন্ত্র
    0.44
    werben
    0.44
    र्चे
    0.44
    ilibus
    0.43
     বিদ্যমান
    0.43
    南極
    0.43
    jer
    0.43
    POSITIVE LOGITS
    naires
    0.60
     exce
    0.47
    意
    0.47
     intención
    0.45
     payloads
    0.45
     arbitr
    0.45
     evade
    0.45
     goles
    0.44
     aides
    0.44
    バード
    0.44
    Activations Density 0.000%

    No Known Activations