© 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. 93005
    Prev
    Next
    INDEX
    Explanations

    official

    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
    Omega
    0.47
    security
    0.46
    S
    0.44
     security
    0.44
    AED
    0.44
    [
    0.43
     company
    0.43
    కునే
    0.42
    Listo
    0.41
     dispenser
    0.40
    POSITIVE LOGITS
     официально
    0.60
     офі
    0.59
     официа
    0.58
     oficiais
    0.58
    offic
    0.55
     conund
    0.54
     officielles
    0.54
    <unused361>
    0.54
     인한
    0.53
     oficial
    0.53
    Activations Density 0.001%

    No Known Activations