© 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. 105104
    Prev
    Next
    INDEX
    Explanations

    us a call or your review

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

    foreign 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
    inally
    0.52
    to
    0.50
    ığı
    0.50
    o
    0.48
     لأن
    0.48
    ,
    0.47
    Because
    0.46
     নিজেকে
    0.45
     thys
    0.44
    、
    0.44
    POSITIVE LOGITS
     indiquer
    0.50
    ᖅ
    0.49
     intest
    0.47
     belirt
    0.47
    اہم
    0.46
     conti
    0.46
    ید
    0.45
     diva
    0.45
     tropic
    0.45
     cinq
    0.44
    Activations Density 0.082%

    No Known Activations