© 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. 146027
    Prev
    Next
    INDEX
    Explanations

    common words followed by specific words

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

    fitting, color, CEOs, order, directly

    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
     gare
    0.52
     greatly
    0.49
    aremos
    0.48
    Rain
    0.47
     mo
    0.47
    ين
    0.46
    A
    0.46
     আমরা
    0.46
     appreciably
    0.45
     mcc
    0.45
    POSITIVE LOGITS
    esy
    0.43
     अडानी
    0.42
     महिन
    0.42
    的人
    0.41
    啲
    0.40
    ऩ
    0.40
    的問題
    0.40
    ocrates
    0.39
    两国
    0.39
     Jasmin
    0.39
    Activations Density 0.002%

    No Known Activations