© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18278
    Prev
    Next
    INDEX
    Explanations

    steal usernames and card data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -}$
    0.41
    збе
    0.39
    icent
    0.39
     మాత్రమే
    0.38
    ңа
    0.38
    tsky
    0.37
    šić
    0.37
    ೕ
    0.37
    तेला
    0.37
    ManagerProxy
    0.37
    POSITIVE LOGITS
     cuanto
    0.41
     hoher
    0.40
     hues
    0.38
     régler
    0.37
     فهو
    0.37
     modifiers
    0.37
     rufo
    0.37
     glist
    0.36
     cuatro
    0.36
     dürfte
    0.36
    Activations Density 0.032%

    No Known Activations