© 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. 63773
    Prev
    Next
    INDEX
    Explanations

    fine-tuned for tasks

    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
    难
    0.51
    ⺆
    0.48
     무료
    0.46
    ༢
    0.46
     그것
    0.46
     көп
    0.46
    权力
    0.46
    앜
    0.46
    呔
    0.45
     Aralık
    0.44
    POSITIVE LOGITS
     creams
    0.45
    diagonal
    0.43
    following
    0.43
     el
    0.42
     flowers
    0.42
     following
    0.41
     angolo
    0.41
       
    0.41
     ${\
    0.41
     clover
    0.41
    Activations Density 0.004%

    No Known Activations