© 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. 212878
    Prev
    Next
    INDEX
    Explanations

    sequences after specific words

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

    provoking strong feelings

    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
    0.51
    BUT
    0.48
    Too
    0.43
    JM
    0.42
    단
    0.42
    記
    0.41
    женных
    0.40
    江
    0.40
    ＝
    0.40
    JH
    0.39
    POSITIVE LOGITS
     அலங்க
    0.56
     Kana
    0.54
     difficulté
    0.52
     einmal
    0.52
     ChAT
    0.51
     HEX
    0.50
     Hez
    0.50
     შედ
    0.50
    yatiti
    0.49
     Chromat
    0.49
    Activations Density 0.001%

    No Known Activations