© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 96587
    Prev
    Next
    INDEX
    Explanations

    lastly, finally, and concluding items

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

    last or finally

    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
     (
    0.47
    ≈
    0.42
    媲
    0.41
    ؟
    0.41
    2
    0.41
     («
    0.40
     (“
    0.40
    ？
    0.39
    =
    0.39
    ym
    0.38
    POSITIVE LOGITS
     lastly
    1.41
     Lastly
    1.38
    Lastly
    1.27
     infine
    1.11
     finally
    1.01
    最後に
    0.98
     enfin
    0.93
     Finally
    0.93
    finally
    0.93
    Finally
    0.92
    Activations Density 0.087%

    No Known Activations