© 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. 63035
    Prev
    Next
    INDEX
    Explanations

    anomaly, glitch, fracture, unstable

    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
     również
    0.44
    밀
    0.42
     전
    0.42
     perro
    0.41
     수
    0.41
     &
    0.41
     också
    0.40
    Body
    0.40
    a
    0.40
    比如
    0.39
    POSITIVE LOGITS
     hMut
    0.44
    зна
    0.38
     disconcert
    0.38
     unstimulated
    0.38
    தியின்
    0.38
     शिफ्ट
    0.38
     dehydrogenase
    0.38
     પ્રાર્થના
    0.37
     いる
    0.36
     disequ
    0.36
    Activations Density 0.016%

    No Known Activations