© 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. 156624
    Prev
    Next
    INDEX
    Explanations

    posted on

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

    describing potential strengths or angles

    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
     sangue
    0.49
    ساس
    0.48
     кров
    0.46
     ktorí
    0.44
     პ
    0.43
    ຕະ
    0.43
    ۰
    0.43
    ETT
    0.42
    粲
    0.42
     ένας
    0.41
    POSITIVE LOGITS
    방법
    0.51
     继续
    0.50
    henden
    0.49
    حه
    0.48
    går
    0.46
    屏幕
    0.46
    键盘
    0.46
     fusion
    0.45
    ből
    0.45
    accueil
    0.44
    Activations Density 0.000%

    No Known Activations