© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159953
    Prev
    Next
    INDEX
    Explanations

    step up, step out, step forward

    np_acts-logits-general · gemini-2.5-flash-lite

    step away or outside

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ı
    0.51
     sepanjang
    0.50
     stren
    0.49
    कश
    0.48
     setempat
    0.47
     ISR
    0.47
    ഌ
    0.47
     सहमति
    0.46
     শীর্ষ
    0.46
    riente
    0.46
    POSITIVE LOGITS
    stepping
    0.84
    Step
    0.82
     stepped
    0.80
     stepping
    0.80
     Step
    0.75
    步
    0.74
    step
    0.73
     step
    0.71
    一步
    0.71
    STEP
    0.62
    Activations Density 0.065%

    No Known Activations