© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40152
    Prev
    Next
    INDEX
    Explanations

    protection and advocacy

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

    after certain words

    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
    囝
    0.50
     Collaborative
    0.48
    睬
    0.46
    儁
    0.46
     gtk
    0.46
    绕
    0.46
     Nodo
    0.46
     Règles
    0.46
    لن
    0.45
     PTH
    0.45
    POSITIVE LOGITS
    foreground
    0.55
    weapon
    0.52
    বাহিত
    0.49
    drug
    0.48
    dental
    0.48
    ecie
    0.48
    t
    0.47
    textColor
    0.46
    aurant
    0.46
    фин
    0.46
    Activations Density 0.000%

    No Known Activations