© 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. 224485
    Prev
    Next
    INDEX
    Explanations

    cannot outsource

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

    truly assist, constantly rescue, fully satisfy

    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
    sim
    0.50
    at
    0.48
    type
    0.48
    老的
    0.46
    bridge
    0.46
    bi
    0.45
    Cy
    0.45
    。
    0.45
    drop
    0.44
    পি
    0.44
    POSITIVE LOGITS
     オン
    0.54
    未満
    0.51
     ներ
    0.50
    坫
    0.49
     بام
    0.48
     温
    0.47
     値
    0.47
     だっ
    0.47
     กำ
    0.47
     聞い
    0.47
    Activations Density 0.000%

    No Known Activations