© 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. 243960
    Prev
    Next
    INDEX
    Explanations

    subject, other, at, integration, rejected, that, or, should

    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
     轻
    0.53
     oryg
    0.49
     اكت
    0.49
     tutaj
    0.47
    们
    0.47
    了大
    0.46
    們
    0.46
     πο
    0.46
    rification
    0.45
    markt
    0.44
    POSITIVE LOGITS
    ソン
    0.53
    Cho
    0.51
    стройство
    0.49
    筑
    0.49
    ς
    0.49
     transduction
    0.48
     vasodil
    0.47
    vitamin
    0.46
     cytok
    0.46
    embedding
    0.46
    Activations Density 0.001%

    No Known Activations