© 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. 99369
    Prev
    Next
    INDEX
    Explanations

    bought online and crimes committed

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

    legal or private contexts

    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
    ffin
    0.48
    Miscellaneous
    0.46
    Pie
    0.44
     Evernote
    0.43
    换
    0.43
     mainframe
    0.43
     Marketing
    0.42
     briefcase
    0.42
    ffes
    0.42
     tasks
    0.41
    POSITIVE LOGITS
     (\<
    0.47
    cevam
    0.46
    ἤ
    0.44
    군은
    0.44
    
    0.44
     razão
    0.43
     subtração
    0.43
     azimuthal
    0.42
    minValue
    0.41
     quân
    0.41
    Activations Density 0.001%

    No Known Activations