© 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. 188183
    Prev
    Next
    INDEX
    Explanations

    looking nice, patterns., my nursery, the called, are there, to be, its sitting, favorite glass, believe in, those elections

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

    container, CPU, flow

    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
     and
    0.48
    on
    0.42
    分为
    0.41
    isOn
    0.41
    &
    0.41
    uni
    0.41
     &\
    0.41
    esk
    0.40
    分成
    0.40
     l
    0.40
    POSITIVE LOGITS
     تلیفون
    0.52
     этими
    0.51
    ковым
    0.49
     পাকিস্ত
    0.48
     कनेक्टिविटी
    0.48
    тным
    0.47
     بلکه
    0.47
     इमार
    0.47
     वीरता
    0.46
    ທ່ານ
    0.46
    Activations Density 0.000%

    No Known Activations