© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 109518
    Prev
    Next
    INDEX
    Explanations

    multilingual services

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

    acting on behalf of another

    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
    accounts
    0.44
    z
    0.44
     dates
    0.44
    contraction
    0.43
     Cameron
    0.41
    s
    0.41
    loss
    0.41
     fiat
    0.40
    j
    0.39
    ‘
    0.39
    POSITIVE LOGITS
     যাত্রী
    0.53
    Penumpang
    0.52
     ভে
    0.52
     рыб
    0.50
     tathapi
    0.48
    alamy
    0.47
    ონი
    0.47
    ಂಟು
    0.47
     所以
    0.47
     さらに
    0.47
    Activations Density 0.000%

    No Known Activations