© 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. 200810
    Prev
    Next
    INDEX
    Explanations

    digestion, organization, status

    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
     trialComponents
    0.52
    ፫
    0.52
    erosene
    0.50
     लेकिन
    0.49
    ന്നി
    0.48
     Несмотря
    0.47
     Tüm
    0.47
     şek
    0.46
    栏
    0.46
     sAlarm
    0.46
    POSITIVE LOGITS
    اف
    0.50
    త
    0.42
    violent
    0.42
    ساز
    0.42
     باز
    0.41
    tense
    0.40
     शक्ती
    0.40
     acta
    0.40
     расход
    0.39
    இய
    0.38
    Activations Density 0.000%

    No Known Activations