© 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-65K
    7. 5251
    Prev
    Next
    INDEX
    Explanations

    actions that follow verbs or set conditions

    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_65k_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
     otros
    0.48
     outros
    0.47
     qualcuno
    0.46
    ENGTH
    0.44
     autres
    0.43
     anderes
    0.42
     alguien
    0.42
    <unused50>
    0.42
     drugih
    0.42
     criminality
    0.42
    POSITIVE LOGITS
     three
    0.71
    the
    0.65
     the
    0.64
    three
    0.63
     two
    0.63
     four
    0.61
     five
    0.57
     seven
    0.55
    two
    0.54
     மூன்று
    0.54
    Activations Density 0.193%

    No Known Activations