© 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. 33186
    Prev
    Next
    INDEX
    Explanations

    massive objects

    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
    тельный
    0.41
     वोल्ट
    0.40
     Nhưng
    0.40
    辊
    0.40
     нужна
    0.39
    adă
    0.39
    马上
    0.39
    ంచెం
    0.39
     அதிசயம்
    0.39
     একটু
    0.38
    POSITIVE LOGITS
     invariably
    0.46
    Soviet
    0.43
    her
    0.41
    <unused2200>
    0.41
    enseit
    0.40
     subjug
    0.40
    <unused2135>
    0.38
     Soviet
    0.38
     vedno
    0.38
     moderne
    0.38
    Activations Density 0.005%

    No Known Activations