© 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. 40-GEMMASCOPE-2-RES-262K
    7. 14211
    Prev
    Next
    INDEX
    Explanations

    my / your wife

    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_40_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
    pletely
    0.37
    在家
    0.35
    ните
    0.35
    𝗄
    0.33
    ಿಗೆ
    0.33
     taken
    0.32
    াসা
    0.32
    iquetas
    0.32
     bulld
    0.32
    rupa
    0.31
    POSITIVE LOGITS
     τῶν
    0.39
    뺑
    0.36
     иллю
    0.35
    ڭ
    0.35
    Il
    0.35
    ILL
    0.34
    子ども
    0.33
     yě
    0.33
     voork
    0.33
     veía
    0.33
    Activations Density 0.000%

    No Known Activations