© 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. 29656
    Prev
    Next
    INDEX
    Explanations

    specific groups or topics

    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
     stratégie
    0.41
     flaw
    0.40
    磋
    0.40
    Calibration
    0.39
     xray
    0.39
     calibration
    0.38
     சிந்த
    0.38
     captcha
    0.37
     coolant
    0.37
     estrategias
    0.37
    POSITIVE LOGITS
     евре
    0.52
     homosexuality
    0.47
     Israel
    0.44
     Jewish
    0.43
    부
    0.43
     মুসলমানদের
    0.43
     Africa
    0.43
     {}\
    0.42
     Yugoslavia
    0.42
     العرب
    0.42
    Activations Density 0.028%

    No Known Activations