© 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. 54687
    Prev
    Next
    INDEX
    Explanations

    phone number or url

    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
    協助
    0.45
    արկ
    0.44
     допомо
    0.44
     aiuto
    0.43
    관리
    0.42
     phoned
    0.42
    otherapie
    0.41
    昻
    0.39
     আরো
    0.39
     দোক
    0.39
    POSITIVE LOGITS
     epistem
    0.48
     portray
    0.44
     implicitly
    0.43
     pith
    0.43
     jurispr
    0.39
     inherently
    0.39
     pleasantly
    0.39
    '.
    0.38
     plen
    0.38
     ecologically
    0.38
    Activations Density 0.042%

    No Known Activations