© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110643
    Prev
    Next
    INDEX
    Explanations

    navigation and reporting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виртуа
    0.47
     ос
    0.46
     spurred
    0.46
     reliance
    0.45
    땡
    0.43
     unido
    0.43
     impacting
    0.43
     chasing
    0.42
     portrayal
    0.42
    emphasis
    0.42
    POSITIVE LOGITS
     Sensor
    0.49
     Displacement
    0.48
     Torque
    0.47
     Sent
    0.46
     Sensing
    0.46
     Destination
    0.46
     Raffle
    0.44
    嚧
    0.44
     Ticket
    0.44
    Connector
    0.44
    Activations Density 0.003%

    No Known Activations