© 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. 15670
    Prev
    Next
    INDEX
    Explanations

    saving code as a file

    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
     F
    0.51
     R
    0.50
     through
    0.47
     resource
    0.46
     H
    0.44
     lewat
    0.44
     tr
    0.44
     accessed
    0.43
    R
    0.42
     run
    0.42
    POSITIVE LOGITS
    ꒪
    0.42
    perse
    0.40
    یعنی
    0.39
    terminology
    0.39
     కలిగి
    0.39
    寢
    0.39
     conceptions
    0.39
     लैंग्वे
    0.38
    ⃘
    0.38
     смы
    0.38
    Activations Density 0.099%

    No Known Activations