© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15156
    Prev
    Next
    INDEX
    Explanations

    bullet points and lists

    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
     differentiable
    0.45
     subsequence
    0.45
    次
    0.45
     thrombosis
    0.42
    半
    0.42
    Append
    0.42
     undergo
    0.42
    2
    0.42
    Spatial
    0.40
    ική
    0.40
    POSITIVE LOGITS
     meinen
    0.54
     Sudah
    0.54
     meu
    0.52
     saya
    0.51
     kapsamında
    0.51
     basura
    0.50
    siehe
    0.50
     yukarı
    0.50
     bagus
    0.49
     Bahan
    0.49
    Activations Density 0.008%

    No Known Activations