© 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. 105871
    Prev
    Next
    INDEX
    Explanations

    `during` or `concluding`

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

    emotional fallout, grief, betrayal

    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
     "
    0.50
    ’
    0.50
     advantage
    0.46
     y
    0.46
     new
    0.45
     advantages
    0.44
     Advantages
    0.44
     duplicates
    0.43
     '
    0.43
     fortunate
    0.42
    POSITIVE LOGITS
     commemorated
    0.50
     воспомина
    0.49
    各国
    0.48
     tragedia
    0.48
    tuvo
    0.47
     trauer
    0.47
    惋
    0.47
     दुनियाभर
    0.46
    şiktaş
    0.46
    utebol
    0.46
    Activations Density 0.001%

    No Known Activations