© 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. 15796
    Prev
    Next
    INDEX
    Explanations

    I'm self-identification

    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
     తన
    0.56
    くれました
    0.51
    আমার
    0.48
     തന്റെ
    0.46
     humbled
    0.45
    ませんでした
    0.44
    <unused26>
    0.43
    他也
    0.43
    讓我
    0.43
     अटेम्प्ट
    0.43
    POSITIVE LOGITS
     consists
    0.63
     originates
    0.52
     is
    0.52
     है
    0.51
     contains
    0.51
     occurs
    0.50
     เป็น
    0.50
     brukes
    0.50
     состоит
    0.48
     происходит
    0.47
    Activations Density 0.047%

    No Known Activations