© 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. 36045
    Prev
    Next
    INDEX
    Explanations

    discussing accessibility, important learnings

    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
     предусматри
    0.49
    ૉ
    0.49
    𝐻
    0.47
    Ꮘ
    0.47
    ંભ
    0.47
    <unused506>
    0.46
    <unused1002>
    0.45
    媲
    0.44
    ഔ
    0.44
    妧
    0.44
    POSITIVE LOGITS
     sort
    0.56
     very
    0.55
    sort
    0.54
    very
    0.53
    這樣子
    0.52
     really
    0.52
    _
    0.52
    ことを
    0.51
     things
    0.50
     uh
    0.50
    Activations Density 0.027%

    No Known Activations