© 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. 19748
    Prev
    Next
    INDEX
    Explanations

    code and technical explanations

    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
     জেলে
    0.44
    <unused1112>
    0.42
     ਜਾ
    0.41
    -<
    0.40
    統一
    0.39
    θυ
    0.38
    📔
    0.38
    ltry
    0.38
     어려
    0.38
     económicos
    0.38
    POSITIVE LOGITS
     இந்த
    0.46
     surrounds
    0.43
     peripheral
    0.40
     бара
    0.40
    ↵↵
    0.39
    reif
    0.39
     weitere
    0.38
    はこの
    0.38
    对他
    0.38
    на
    0.37
    Activations Density 0.001%

    No Known Activations