© 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. 134715
    Prev
    Next
    INDEX
    Explanations

    condition for decision

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

    written by, frequent the, keywords from, votes against, drinks $\frac{6}{6}$, Seconds are, Periods added

    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
     anywhere
    0.50
     進
    0.48
     അയ
    0.47
    ESSAGE
    0.44
    atic
    0.43
     пле
    0.43
    attle
    0.42
    ôle
    0.42
    s
    0.42
     তাত
    0.42
    POSITIVE LOGITS
     numai
    0.50
    گیز
    0.48
    _*
    0.48
    水源
    0.47
    ၻ
    0.46
     allerede
    0.44
    ਇ
    0.44
     liz
    0.44
    だって
    0.44
    啤酒
    0.44
    Activations Density 0.000%

    No Known Activations