© 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. 71652
    Prev
    Next
    INDEX
    Explanations

    counting units like days or nights

    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
    讠
    0.48
     هذه
    0.43
    不僅
    0.43
    ovatel
    0.42
    avasena
    0.42
    тную
    0.41
    nél
    0.40
     эту
    0.40
     تخ
    0.40
    TorpedoStore
    0.40
    POSITIVE LOGITS
     K
    0.46
     U
    0.43
     FileNotFound
    0.42
     approaches
    0.42
     spawn
    0.41
     topology
    0.41
     highlights
    0.40
     Highlight
    0.40
     desired
    0.40
     row
    0.39
    Activations Density 0.001%

    No Known Activations