© 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. 63585
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases

    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
    +
    0.42
     definite
    0.39
     termasuk
    0.39
     constantly
    0.38
    ರ್ಗ
    0.38
     F
    0.38
    $
    0.38
    你有
    0.38
     ARR
    0.38
     incluso
    0.37
    POSITIVE LOGITS
    ladi
    0.53
     रझा
    0.52
    დება
    0.50
     повре
    0.50
     şeker
    0.50
    ího
    0.50
    úly
    0.49
     což
    0.48
     vért
    0.48
    جين
    0.48
    Activations Density 0.009%

    No Known Activations