© 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. 76324
    Prev
    Next
    INDEX
    Explanations

    final decision

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

    electrical and chemical energy storage

    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
     hardship
    0.48
     poverty
    0.45
     lords
    0.45
     witchcraft
    0.45
     strife
    0.45
    grace
    0.45
     assembly
    0.45
    YN
    0.45
    ’
    0.44
    POSITIVE LOGITS
     इनटू
    0.54
     فونٹ
    0.49
    鋈
    0.48
     crecer
    0.48
     намного
    0.45
    匼
    0.44
    烀
    0.43
    茛
    0.43
    vég
    0.42
    Deploy
    0.42
    Activations Density 0.004%

    No Known Activations