© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 61463
    Prev
    Next
    INDEX
    Explanations

    dialogue speaker names

    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
    退出
    0.48
     webcast
    0.44
    残留
    0.42
     quieras
    0.42
    είς
    0.42
     gotta
    0.41
     hypothalamus
    0.40
    夠
    0.40
     dedos
    0.40
     pretzels
    0.40
    POSITIVE LOGITS
     był
    0.42
    stantially
    0.42
    ۱۹
    0.42
    «
    0.42
     była
    0.41
     již
    0.39
     byla
    0.39
     была
    0.39
    0.38
    ributor
    0.38
    Activations Density 0.005%

    No Known Activations