© 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. 231930
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ওয়া
    0.40
    职
    0.40
    தமி
    0.40
    சிக்கும்
    0.39
    টিল
    0.39
     cuy
    0.39
    టీ
    0.39
     fixture
    0.38
    রাষ্ট্রম
    0.38
    珹
    0.38
    POSITIVE LOGITS
     indetermin
    0.41
    TRS
    0.40
     Domb
    0.39
    떳
    0.39
     demoral
    0.38
     Yous
    0.38
    Textbox
    0.38
    over
    0.37
     منهم
    0.37
    TP
    0.36
    Activations Density 0.002%

    No Known Activations