© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15768
    Prev
    Next
    INDEX
    Explanations

    code examples

    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_65k_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
     aunque
    0.47
     although
    0.47
     nejen
    0.46
     ولكن
    0.45
    although
    0.44
     ;$
    0.44
     ebenfalls
    0.44
    ?;
    0.43
    aunque
    0.43
     również
    0.41
    POSITIVE LOGITS
     आणि
    0.49
     weird
    0.44
     ਅਤੇ
    0.43
     있어서
    0.43
     கட்டமை
    0.43
     그리고
    0.43
     এবং
    0.40
    ভাবে
    0.40
    そして
    0.39
    安慰
    0.39
    Activations Density 0.035%

    No Known Activations