© 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. 29016
    Prev
    Next
    INDEX
    Explanations

    sequences before access

    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
    👛
    0.48
     設定
    0.47
    色が
    0.47
    シリーズ
    0.46
    ঞ্চি
    0.46
    놓
    0.46
    𝙊
    0.46
    었는데
    0.45
    ц
    0.45
    뻤
    0.43
    POSITIVE LOGITS
     invade
    0.51
     upstream
    0.49
     beforehand
    0.48
     acquires
    0.47
     outperforms
    0.47
     threatens
    0.46
     upon
    0.45
     overland
    0.45
     threaten
    0.45
     mộ
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.