© 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. 98510
    Prev
    Next
    INDEX
    Explanations

    unstained or pristine

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

    amplify, compress, RCA, writing

    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
    far
    0.53
     mezzi
    0.52
     hems
    0.51
     tyle
    0.49
     ew
    0.49
     interventi
    0.49
     w
    0.48
     delikat
    0.48
     schneller
    0.47
    wys
    0.47
    POSITIVE LOGITS
    Би
    0.55
    ме
    0.54
    飲
    0.52
    ди
    0.52
    ។
    0.50
    ла
    0.49
     Букмекер
    0.49
    హం
    0.48
    это
    0.48
     Казино
    0.48
    Activations Density 0.001%

    No Known Activations