© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9938
    Prev
    Next
    INDEX
    Explanations

    Reading Integers

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

    The neuron detects terms related to managing motel room reservations (e.g. tracking, assigning, canceling, and displaying room bookings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
    fuck
    0.68
    Fuck
    0.66
     fucked
    0.65
    Colombia
    0.65
    Notably
    0.65
    NewUrl
    0.63
    迦
    0.62
    Notable
    0.62
     campaña
    0.61
    UpdatedAt
    0.61
    POSITIVE LOGITS
     processing
    0.75
     infile
    0.73
    <0x0B>
    0.71
    }//
    0.69
     Bergeron
    0.68
    
    0.68
     JOptionPane
    0.68
     }//
    0.67
    
    0.66
     tote
    0.65
    Activations Density 0.039%

    No Known Activations