© 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. 124615
    Prev
    Next
    INDEX
    Explanations

    registered to vote

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

    generating alternative phrasings

    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
    -"
    0.48
     тези
    0.48
     bothering
    0.48
     දැන්
    0.48
    ных
    0.46
     CWE
    0.46
     acceptance
    0.45
    每月
    0.45
    t
    0.45
     З
    0.44
    POSITIVE LOGITS
    DNA
    0.48
    MenuStyle
    0.47
     połą
    0.46
     wobec
    0.43
     کیلوم
    0.43
     zależ
    0.43
     odpow
    0.42
    ﺟ
    0.41
    ientos
    0.41
    رمی
    0.41
    Activations Density 0.001%

    No Known Activations