© 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-16K
    7. 11528
    Prev
    Next
    INDEX
    Explanations

    contrast or correction

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

    actually / in reality

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

    actually

    np_max-act-logits · claude-4-5-sonnet
    Triggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     وَ
    0.44
     ので
    0.42
    okkal
    0.42
    ourcen
    0.40
    ủ
    0.40
    咱们
    0.40
     зачем
    0.40
     आरोग्य
    0.38
    olist
    0.38
    𝚊
    0.38
    POSITIVE LOGITS
     actually
    0.82
     Actually
    0.82
    其实
    0.76
    其實
    0.75
    actually
    0.71
    Actually
    0.70
     sebenarnya
    0.68
     aslında
    0.66
     nope
    0.65
    实际上
    0.63
    Activations Density 0.292%

    No Known Activations