© 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. 53753
    Prev
    Next
    INDEX
    Explanations

    colleague and friend

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

    profit and loss

    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
    dispatcher
    0.51
     Kamath
    0.48
    impulan
    0.47
     Бере
    0.45
    2
    0.45
    ua
    0.44
     was
    0.44
    6
    0.43
    had
    0.43
     had
    0.43
    POSITIVE LOGITS
     মৃত্য
    0.45
     സൂ
    0.45
    強い
    0.44
    profitLoss
    0.44
    毗
    0.44
     negócios
    0.43
     বিনিয়োগ
    0.43
     interessi
    0.42
     adversity
    0.42
    創新
    0.42
    Activations Density 0.000%

    No Known Activations