© 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. 12273
    Prev
    Next
    INDEX
    Explanations

    purpose or situation context

    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
    ementerian
    0.31
    <unused2130>
    0.29
    㤟
    0.26
    विशेष
    0.25
    ﺝ
    0.25
     অথবা
    0.25
    ⓑ
    0.25
    <unused2126>
    0.25
    ̙
    0.24
    ⓛ
    0.24
    POSITIVE LOGITS
     przypadku
    0.38
     casos
    0.38
     cases
    0.35
     situations
    0.33
     случаи
    0.32
     scenarios
    0.30
     випадку
    0.30
     لاءِ
    0.29
    osomal
    0.29
     achieving
    0.29
    Activations Density 0.221%

    No Known Activations