© 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-16K
    7. 1094
    Prev
    Next
    INDEX
    Explanations

    formula looks

    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_16k_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
    ಃ
    0.41
    ાર
    0.39
    oggetto
    0.37
    ißler
    0.36
    |.|.|
    0.36
     ವಸ್ತು
    0.36
    Kaynak
    0.36
    𝗂
    0.36
    <unused2066>
    0.36
    ్ఞ
    0.35
    POSITIVE LOGITS
    ,
    0.48
     has
    0.42
     in
    0.41
     on
    0.40
     full
    0.39
     (
    0.39
     from
    0.39
     to
    0.39
     had
    0.38
     a
    0.37
    Activations Density 2.683%

    No Known Activations