© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2153
    Prev
    Next
    INDEX
    Explanations

    stairs and building components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    rab
    1.43
    ainder
    1.31
    伶
    1.29
     특집
    1.21
    roga
    1.19
     Clipping
    1.17
    ests
    1.15
    ゾート
    1.15
    bola
    1.14
    arters
    1.12
    POSITIVE LOGITS
     toward
    1.94
     towards
    1.90
     staircase
    1.86
     stairs
    1.84
    🪜
    1.81
     hacia
    1.79
     downhill
    1.78
     steps
    1.75
     stair
    1.71
     Stair
    1.68
    Activations Density 0.675%

    No Known Activations