© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 65534
    Prev
    Next
    INDEX
    Explanations

    approximations and ranges

    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
    !’
    0.55
    !»
    0.54
    ！」
    0.52
    !--
    0.50
     메
    0.48
    Ắ
    0.47
    Ꮮ
    0.47
    ！
    0.47
    !`
    0.46
    !")
    0.46
    POSITIVE LOGITS
     khoảng
    0.80
     roughly
    0.76
     ongeveer
    0.75
     approximately
    0.71
     około
    0.71
     aproximadamente
    0.71
     ungefähr
    0.71
    ประมาณ
    0.67
     примерно
    0.66
     approx
    0.66
    Activations Density 0.073%

    No Known Activations