© 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. 111965
    Prev
    Next
    INDEX
    Explanations

    funny jokes and questions

    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
    Hull
    0.44
    VSLU
    0.44
    Balls
    0.44
    Gand
    0.43
    Là
    0.43
     DIFFICULTY
    0.43
    𝕡
    0.43
     circuitry
    0.42
    φαι
    0.42
    Nucle
    0.42
    POSITIVE LOGITS
     TikTok
    0.42
    ί
    0.42
     JV
    0.41
     Charter
    0.40
     pants
    0.40
     Youtube
    0.40
    otion
    0.39
    ני
    0.39
     YouTube
    0.39
    кнове
    0.39
    Activations Density 0.007%

    No Known Activations