Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 467
    Prev
    Next
    INDEX
    Explanations

    .input, .maze, .cars

    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
     wodurch
    0.22
     contaminant
    0.20
     waardoor
    0.20
    GreaterThan
    0.20
     whereupon
    0.19
     그리고
    0.19
    禽
    0.18
     gleichen
    0.18
     deaminase
    0.18
    Snapped
    0.18
    POSITIVE LOGITS
     t
    0.25
    ният
    0.24
     پیسې
    0.23
     officia
    0.23
     started
    0.22
     have
    0.22
     acuerdo
    0.22
    まずは
    0.21
    startTime
    0.21
     start
    0.21
    Activations Density 0.256%

    No Known Activations