© 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. 1343
    Prev
    Next
    INDEX
    Explanations

    how things are called

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

    nicknames and alternative names

    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
    ới
    0.46
     toekomst
    0.44
    च्युअल
    0.41
     szükséges
    0.41
    があれば
    0.41
     tirar
    0.40
     sogen
    0.40
     делать
    0.39
     "~
    0.39
    POSITIVE LOGITS
     colloqu
    0.46
     according
    0.42
    adia
    0.40
     rifer
    0.39
    refer
    0.39
     оши
    0.38
    ことから
    0.38
     唐
    0.38
     Collo
    0.38
     sobri
    0.38
    Activations Density 0.054%

    No Known Activations