© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44887
    Prev
    Next
    INDEX
    Explanations

    disappearing messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ư
    0.45
    ø
    0.45
    rasp
    0.45
     Bayou
    0.43
     استخدم
    0.43
     ஏற்று
    0.42
     फार्मा
    0.42
    readFile
    0.42
     rossa
    0.42
     अनुभवी
    0.42
    POSITIVE LOGITS
    지
    0.44
     prur
    0.40
     fulfils
    0.39
     বোধ
    0.39
     laughs
    0.39
     reproducibility
    0.38
     foes
    0.38
     indulged
    0.38
     approbation
    0.38
     equivoc
    0.38
    Activations Density 0.002%

    No Known Activations