© 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. 4565
    Prev
    Next
    INDEX
    Explanations

    on your instructions

    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
    嚨
    0.41
    後半
    0.39
    導數
    0.38
    ᄍ
    0.38
    entrale
    0.37
     صہی
    0.37
    <unused260>
    0.36
     желез
    0.36
    弐
    0.36
    വുമായ
    0.36
    POSITIVE LOGITS
    报
    0.38
     policies
    0.37
    AMENTO
    0.37
    谋
    0.37
    CRIPT
    0.35
     المعروف
    0.34
     guideline
    0.34
    policies
    0.34
     hobbies
    0.34
     Existen
    0.34
    Activations Density 0.002%

    No Known Activations