© 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. 82622
    Prev
    Next
    INDEX
    Explanations

    when considering

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

    Million BCE

    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
    Negative Logits
     OCTOBER
    0.45
    chetto
    0.45
    漠
    0.45
    ствима
    0.44
     американский
    0.44
     impulso
    0.44
     διαδικ
    0.44
    蓟
    0.43
     aria
    0.43
     esfuerzo
    0.43
    POSITIVE LOGITS
    tä
    0.49
    VS
    0.47
    பே
    0.46
    öl
    0.45
    VD
    0.45
    LED
    0.44
    Liens
    0.44
    lit
    0.44
    Bibliography
    0.44
     входят
    0.44
    Activations Density 0.001%

    No Known Activations