© 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. 25787
    Prev
    Next
    INDEX
    Explanations

    CSS properties following closing parenthesis

    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
     расска
    0.44
     современных
    0.42
     सांगतात
    0.41
     पहुंचे
    0.41
     ደ
    0.40
     современной
    0.40
     ব্র
    0.39
     эта
    0.39
     গড়ে
    0.38
     ờ
    0.38
    POSITIVE LOGITS
    étrico
    0.45
    ény
    0.40
    ከላከ
    0.40
    iny
    0.39
    אין
    0.39
    徃
    0.39
     گاڑی
    0.39
    愀
    0.39
    ission
    0.38
    ini
    0.38
    Activations Density 0.014%

    No Known Activations