© 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. 104321
    Prev
    Next
    INDEX
    Explanations

    Facebook, Instagram, Twitter

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

    urls starting with https

    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
    https
    0.59
     https
    0.48
     Moshe
    0.42
     প্রভাস
    0.41
    槅
    0.40
    Inbox
    0.39
     PDF
    0.39
     INKA
    0.39
     Islands
    0.39
    ✷
    0.39
    POSITIVE LOGITS
    щает
    0.44
     crece
    0.43
    жают
    0.40
    WWW
    0.39
     aang
    0.39
     расту
    0.38
     obesidad
    0.38
     என்கிறார்
    0.38
     svar
    0.38
    жает
    0.37
    Activations Density 0.035%

    No Known Activations