© 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. 34366
    Prev
    Next
    INDEX
    Explanations

    intense physical or emotional shock

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

    sudden physical or emotional reactions

    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
     `>=`,
    0.42
     blames
    0.41
     distrust
    0.41
     blaming
    0.41
     hinting
    0.40
    ре
    0.40
    ве
    0.40
    ৃঙ্খ
    0.39
    রামর্শ
    0.39
     disgruntled
    0.39
    POSITIVE LOGITS
     screech
    0.46
     полости
    0.43
    唖
    0.43
    utia
    0.42
     양
    0.41
    ulio
    0.41
     tremble
    0.40
     stell
    0.39
     Lucio
    0.39
     rach
    0.39
    Activations Density 0.050%

    No Known Activations