© 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. 22313
    Prev
    Next
    INDEX
    Explanations

    based on

    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
    ША
    0.47
    Ц
    0.44
    лем
    0.44
    daniel
    0.44
    Пер
    0.43
    П
    0.43
    лове
    0.41
    լ
    0.41
    Ե
    0.41
    Гра
    0.41
    POSITIVE LOGITS
     all
    0.62
     many
    0.59
     content
    0.56
     oil
    0.55
     optimize
    0.55
     food
    0.54
     improve
    0.54
     bread
    0.54
     comparing
    0.53
     people
    0.52
    Activations Density 0.002%

    No Known Activations