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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 4893
    Prev
    Next
    INDEX
    Explanations

    song structure markers

    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
    .
    0.25
     C
    0.20
     A
    0.20
     V
    0.20
    ,
    0.20
    ↵↵
    0.20
     S
    0.19
     I
    0.19
     F
    0.19
     K
    0.19
    POSITIVE LOGITS
     murderous
    0.21
    <unused1060>
    0.21
    righteous
    0.20
    Й
    0.20
     ಹೊಸ
    0.20
    แมนเชสเตอร์ซิตี
    0.20
    StockDel
    0.20
    िरपेक्ष
    0.20
    <unused1083>
    0.20
    <unused1158>
    0.20
    Activations Density 2.790%

    No Known Activations