© 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. 111529
    Prev
    Next
    INDEX
    Explanations

    last year, universe, strategy

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

    "General" followed by a category

    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
     succeeding
    0.47
     might
    0.46
     &
    0.46
     recognized
    0.44
     negated
    0.44
     nCurrent
    0.44
     mentored
    0.43
     succeeded
    0.43
     (‘
    0.43
     continued
    0.42
    POSITIVE LOGITS
    以前
    0.55
    去年
    0.53
     నేను
    0.52
    ネット
    0.51
    先日
    0.51
     लोकांना
    0.50
    ARCHIVO
    0.48
    ホ
    0.48
    เงิน
    0.47
    昨年
    0.47
    Activations Density 0.001%

    No Known Activations