© 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. 77570
    Prev
    Next
    INDEX
    Explanations

    dispose of drugs

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

    solubility in water

    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
    莆
    0.47
    version
    0.46
    ベン
    0.46
    vero
    0.45
    ன்ஸ்
    0.44
    طر
    0.43
    有了
    0.43
    Ag
    0.42
    Catal
    0.42
    ocap
    0.42
    POSITIVE LOGITS
     щодо
    0.46
     专业
    0.45
     ඇත
    0.45
     ง
    0.45
     совмести
    0.44
    to
    0.44
     三角
    0.44
     塩
    0.43
     assigning
    0.43
     ฝึก
    0.43
    Activations Density 0.003%

    No Known Activations