© 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. 53658
    Prev
    Next
    INDEX
    Explanations

    mom joke

    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
     adsorbed
    0.43
     Нау
    0.43
     가서
    0.43
     $[
    0.42
     대해
    0.42
    名の
    0.42
     adsorption
    0.41
     लगती
    0.39
     daemon
    0.39
    yaar
    0.39
    POSITIVE LOGITS
     نكمل
    0.43
     treball
    0.43
    㚘
    0.42
    ਿਲ
    0.41
    ători
    0.40
     meteen
    0.40
    slu
    0.40
     caméra
    0.40
    屢
    0.40
    规格
    0.40
    Activations Density 0.002%

    No Known Activations