© 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. 29915
    Prev
    Next
    INDEX
    Explanations

    continue or continuation

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

    continue the story or code

    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
     åter
    0.59
    ’
    0.54
    ically
    0.51
     ä
    0.51
    0.51
     är
    0.48
     heraus
    0.48
     einer
    0.47
    irteen
    0.47
    ,
    0.46
    POSITIVE LOGITS
     continuation
    1.30
     continuance
    1.27
     melanjutkan
    1.21
     continued
    1.20
     συνέχ
    1.20
     продол
    1.18
     продолжа
    1.17
     continue
    1.16
    continue
    1.13
     continuar
    1.10
    Activations Density 0.078%

    No Known Activations