© 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. 99886
    Prev
    Next
    INDEX
    Explanations

    discrete packets or chunks

    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
     Schedules
    0.46
     Meet
    0.45
     Scenario
    0.44
     Clay
    0.44
     Corpus
    0.43
    肉
    0.43
     Codes
    0.42
     Regel
    0.42
     Moyen
    0.42
    㺪
    0.42
    POSITIVE LOGITS
    hiti
    0.55
     flyers
    0.54
     magnification
    0.52
     journalists
    0.51
    ca
    0.49
     anten
    0.49
     drugs
    0.48
     impenetrable
    0.48
     antennae
    0.48
     antlers
    0.48
    Activations Density 0.003%

    No Known Activations