© 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. 29180
    Prev
    Next
    INDEX
    Explanations

    spend time or effort

    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
    ب
    0.48
    biggr
    0.46
     classifications
    0.44
    َب
    0.44
     colaboradores
    0.42
    ْب
    0.42
    ados
    0.42
    luv
    0.42
    otions
    0.41
    kings
    0.41
    POSITIVE LOGITS
     पर्यटकों
    0.47
     실제로
    0.45
    是为了
    0.44
     Crisis
    0.44
    🚞
    0.43
     Locomotive
    0.42
    办法
    0.42
     Philippe
    0.42
    高志森
    0.41
     Podczas
    0.41
    Activations Density 0.022%

    No Known Activations