© 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-262K
    7. 19469
    Prev
    Next
    INDEX
    Explanations

    would have children

    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_262k_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
    玛
    0.52
    ্তার
    0.45
     शिवा
    0.44
    
    0.43
    ┎
    0.43
    িল
    0.43
    貉
    0.42
    瑪
    0.41
    曼
    0.40
     판매
    0.40
    POSITIVE LOGITS
     in
    0.44
     singularities
    0.44
     copious
    0.44
     $=
    0.44
     specifying
    0.43
     involves
    0.42
     elucidated
    0.42
    ;"
    0.40
     including
    0.40
    ῖς
    0.40
    Activations Density 0.005%

    No Known Activations