© 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. 14262
    Prev
    Next
    INDEX
    Explanations

    commands and actions

    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
    ו
    0.40
    िक
    0.38
    uhe
    0.36
    uq
    0.36
    <unused458>
    0.35
    の見
    0.34
    OPHY
    0.34
    ̡
    0.34
    핳
    0.34
     relating
    0.33
    POSITIVE LOGITS
     extensively
    0.50
     them
    0.46
     their
    0.46
    了一眼
    0.44
     elkaar
    0.42
     several
    0.41
    一个
    0.41
     incessantly
    0.40
    了一个
    0.40
     various
    0.40
    Activations Density 0.098%

    No Known Activations