© 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. 151946
    Prev
    Next
    INDEX
    Explanations

    foreign sentiment expressions

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

    basketball legends

    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
    '
    0.52
     wrong
    0.51
     consequence
    0.49
     doma
    0.47
    ’
    0.47
    ↵
    0.47
    ↵↵
    0.46
    0.46
     H
    0.46
     paradigms
    0.45
    POSITIVE LOGITS
     মনোরম
    0.55
     聞い
    0.53
    素敵な
    0.52
     прият
    0.50
     delicioso
    0.49
    ोरेशन
    0.48
     जोरदार
    0.48
     lembut
    0.48
     ออก
    0.46
     xinh
    0.46
    Activations Density 0.000%

    No Known Activations