© 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. 170266
    Prev
    Next
    INDEX
    Explanations

    you will

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

    hours pergathering resourcessmaller thanNo leading

    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
     छव
    0.51
     굉장히
    0.47
     segundos
    0.47
    한
    0.46
    पीएस
    0.46
    cnpj
    0.46
     핵심
    0.46
    zend
    0.45
     remise
    0.45
     東京
    0.44
    POSITIVE LOGITS
    Content
    0.43
    ꔹ
    0.41
     thickened
    0.41
    .,
    0.40
     reassuring
    0.40
     selection
    0.40
     billowing
    0.39
     Content
    0.39
     üzerine
    0.39
     Liner
    0.39
    Activations Density 0.001%

    No Known Activations