© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 51361
    Prev
    Next
    INDEX
    Explanations

    numbers and initial states

    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
     bacterias
    0.41
     можли
    0.41
    િ
    0.41
    т
    0.40
    тли
    0.38
    ર
    0.38
    ר
    0.37
    用意
    0.37
    ли
    0.37
     करेगा
    0.36
    POSITIVE LOGITS
     zunächst
    0.47
     three
    0.46
     inicialmente
    0.46
     seven
    0.44
     six
    0.44
     três
    0.43
     ત્રણ
    0.43
     five
    0.42
     Primeiro
    0.42
     primeira
    0.41
    Activations Density 0.003%

    No Known Activations