© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47040
    Prev
    Next
    INDEX
    Explanations

    sequence

    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_65k_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
     옳
    0.55
     고급
    0.50
     존재하는
    0.47
     입
    0.47
     unwittingly
    0.47
    aw
    0.46
     आह
    0.46
     inhab
    0.45
     त्यात
    0.45
     sucedió
    0.45
    POSITIVE LOGITS
    Sensor
    0.47
    北
    0.45
    bin
    0.44
     Elise
    0.44
    EVER
    0.43
    SIGNAL
    0.43
    EMY
    0.43
    Tracker
    0.42
    ToMany
    0.42
    أم
    0.42
    Activations Density 0.006%

    No Known Activations