© 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. 3887
    Prev
    Next
    INDEX
    Explanations

    list item marker

    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
    ClearedBy
    0.26
    <unused629>
    0.25
    <unused2017>
    0.25
     descarg
    0.24
     синх
    0.24
     कहानियां
    0.24
    <unused602>
    0.24
    <unused1881>
    0.24
    <unused585>
    0.23
     homenaje
    0.23
    POSITIVE LOGITS
     required
    0.30
     requested
    0.28
     also
    0.28
     fighter
    0.27
     so
    0.25
     stated
    0.25
     traded
    0.25
     however
    0.25
    required
    0.25
     또한
    0.24
    Activations Density 0.019%

    No Known Activations