© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4712
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with parentheses

    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_262k_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
    anía
    0.30
    atribut
    0.30
     광
    0.30
    tobago
    0.29
    Kaynak
    0.28
     אות
    0.28
     matéria
    0.28
    景观
    0.27
    stethoscope
    0.27
    мара
    0.27
    POSITIVE LOGITS
    ((
    0.35
     the
    0.35
     {
    0.33
     other
    0.32
     ((
    0.32
     D
    0.32
     altered
    0.31
     another
    0.31
     N
    0.31
     new
    0.30
    Activations Density 0.354%

    No Known Activations