© 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. 173558
    Prev
    Next
    INDEX
    Explanations

    death notices and obituaries

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

    locations, states, countries

    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
    ar
    0.50
    -
    0.45
     Ped
    0.45
    W
    0.44
     Battle
    0.43
    ين
    0.43
    mary
    0.43
    ding
    0.42
    enol
    0.42
    an
    0.41
    POSITIVE LOGITS
     criticise
    0.50
     testify
    0.47
     realised
    0.46
     realise
    0.46
     परिमेय
    0.44
     corroborate
    0.43
     capitalise
    0.42
     左
    0.42
     corroborated
    0.42
    左
    0.41
    Activations Density 0.009%

    No Known Activations