© 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. 96284
    Prev
    Next
    INDEX
    Explanations

    words preceding 'explain' or 'learn'

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

    algorithms analyze

    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
    ě
    0.47
    setPassword
    0.46
    issen
    0.42
     ली
    0.41
    ig
    0.41
    ToServer
    0.40
    ísim
    0.40
    lež
    0.40
     balk
    0.40
    ѝ
    0.40
    POSITIVE LOGITS
    ურთი
    0.51
     nutrit
    0.49
    \
    0.48
    Ｈ
    0.47
     памяти
    0.46
     DISTRIBUTION
    0.46
    гій
    0.46
    AlignedText
    0.45
     PROFITS
    0.45
     welcomed
    0.45
    Activations Density 0.000%

    No Known Activations