© 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. 160111
    Prev
    Next
    INDEX
    Explanations

    locations and information

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

    danger unethical tracking political protection

    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
     Salah
    0.46
     exagger
    0.46
     exag
    0.46
    자의
    0.46
     exager
    0.45
    逈
    0.45
     exaggeration
    0.44
     Traum
    0.44
    {
    0.44
    꿋
    0.43
    POSITIVE LOGITS
     museum
    0.45
     museo
    0.44
     botanical
    0.44
     ഇപ്പോള്‍
    0.42
     museums
    0.41
    プログラム
    0.41
    博物館
    0.41
     zoo
    0.41
     музе
    0.40
    mapi
    0.40
    Activations Density 0.001%

    No Known Activations