© 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. 27342
    Prev
    Next
    INDEX
    Explanations

    clear area

    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
     =,
    0.44
    驼
    0.43
     primarily
    0.42
     waterways
    0.42
     其
    0.41
    駝
    0.41
     Ευ
    0.41
    랗
    0.41
    ibraries
    0.40
     northwestern
    0.39
    POSITIVE LOGITS
    ជំងឺ
    0.42
     impre
    0.41
    ீர்
    0.39
     shenanigans
    0.39
     daño
    0.38
    🥴
    0.37
     probabilidad
    0.37
     اچھی
    0.37
     contagion
    0.37
     జరిగిన
    0.37
    Activations Density 0.008%

    No Known Activations