© 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. 29679
    Prev
    Next
    INDEX
    Explanations

    lift and elevating actions

    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
     decreases
    0.49
    減少
    0.47
    ృద్ధి
    0.47
     Flows
    0.47
    á
    0.47
     흐
    0.45
    oj
    0.45
    el
    0.44
    یک
    0.44
    ik
    0.43
    POSITIVE LOGITS
     lifting
    1.18
     lifted
    1.15
     lift
    1.05
     Lift
    1.02
     mengangkat
    1.02
    lifting
    1.01
    Lift
    1.01
     Lifting
    1.00
    lift
    0.99
     подня
    0.95
    Activations Density 0.041%

    No Known Activations