© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 139318
    Prev
    Next
    INDEX
    Explanations

    rumbling, gurgling, UDP

    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
    溂
    0.47
    炁
    0.45
    年后
    0.44
    🤫
    0.44
     сентября
    0.43
     Rusty
    0.43
    🫡
    0.43
     नये
    0.42
    इस
    0.42
    刓
    0.42
    POSITIVE LOGITS
     modality
    0.49
     tópico
    0.47
    	
    0.46
    example
    0.44
     humoral
    0.44
     moiety
    0.44
     motif
    0.42
     inac
    0.41
     cerebro
    0.41
    PACT
    0.41
    Activations Density 0.011%

    No Known Activations