© 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. 124161
    Prev
    Next
    INDEX
    Explanations

    philanthropist Sor George

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

    foreign language phrases and words

    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
     idempot
    0.54
     utile
    0.49
    ยู
    0.46
     martes
    0.46
    onglet
    0.46
    Nest
    0.45
     váy
    0.44
    챱
    0.44
     nectar
    0.43
    휴
    0.43
    POSITIVE LOGITS
    п
    0.47
     unmittel
    0.47
     Altman
    0.47
     beruf
    0.46
     होती
    0.46
    кто
    0.45
    seit
    0.44
     Mills
    0.43
     Mehta
    0.43
     së
    0.43
    Activations Density 0.000%

    No Known Activations