© 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-65K
    7. 48240
    Prev
    Next
    INDEX
    Explanations

    song bridge marker

    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
    сии
    0.46
    оте
    0.44
    ש
    0.44
    সক
    0.43
    󠁳
    0.43
    诡
    0.42
    бу
    0.42
    差不多
    0.42
     дерева
    0.42
    зву
    0.41
    POSITIVE LOGITS
     ⓒ
    0.48
     negotiated
    0.43
     ourselves
    0.42
     cation
    0.42
     sequence
    0.42
     deposited
    0.42
     genomic
    0.42
     creatinine
    0.41
     décrites
    0.41
     από
    0.41
    Activations Density 0.018%

    No Known Activations