© 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. 131328
    Prev
    Next
    INDEX
    Explanations

    currently app backup

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

    narrative and conversational context

    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
     車
    0.51
    ↵
    0.49
     ដោយ
    0.46
     controle
    0.45
     Pharmacy
    0.43
     stone
    0.43
     pra
    0.42
     チェック
    0.41
     Pra
    0.41
     HERE
    0.41
    POSITIVE LOGITS
    이죠
    0.47
     gấp
    0.46
    煅
    0.46
    ނީ
    0.44
     unfolding
    0.44
    新加坡
    0.43
    getMinimum
    0.43
    ↝
    0.43
    룽
    0.42
     astrophys
    0.42
    Activations Density 0.001%

    No Known Activations