© 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-262K
    7. 138274
    Prev
    Next
    INDEX
    Explanations

    speak for themselves

    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
    Ма
    0.52
    ма
    0.50
    瀣
    0.46
     تغيير
    0.46
    ULA
    0.45
     كيف
    0.45
    Quem
    0.43
     だ
    0.42
     울
    0.42
    وتا
    0.42
    POSITIVE LOGITS
     recalling
    0.46
     sendo
    0.44
     being
    0.41
     pretending
    0.41
     apprehend
    0.41
     siendo
    0.40
     deff
    0.40
     perspectivas
    0.40
     codified
    0.40
     redes
    0.40
    Activations Density 0.006%

    No Known Activations