© 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. 44320
    Prev
    Next
    INDEX
    Explanations

    hotel star rating

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

    names and allow/were

    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
    ється
    0.52
    נו
    0.52
    ³/
    0.50
    阿
    0.50
    られた
    0.50
    né
    0.50
    ன்மையான
    0.49
    НЕ
    0.49
    られる
    0.47
    п
    0.47
    POSITIVE LOGITS
     Phillip
    0.52
     Henry
    0.52
     Jackson
    0.50
     Adam
    0.50
     Jerome
    0.49
     Philip
    0.48
     Samson
    0.48
     Hannah
    0.47
     Hamilton
    0.46
     Armstrong
    0.46
    Activations Density 0.000%

    No Known Activations