© 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. 46208
    Prev
    Next
    INDEX
    Explanations

    explicit or generation

    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
     유형
    0.48
    u
    0.48
     قم
    0.46
    わ
    0.45
     домо
    0.44
     호
    0.41
    ೭
    0.41
    उ
    0.41
     உதவிய
    0.41
    纬
    0.40
    POSITIVE LOGITS
     ventric
    0.49
     therapy
    0.48
     Therapy
    0.48
     medicina
    0.46
     nonspecific
    0.46
     sulf
    0.46
     menjalani
    0.46
     phyt
    0.45
     cikin
    0.45
     desempeñ
    0.45
    Activations Density 0.003%

    No Known Activations