© 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. 15482
    Prev
    Next
    INDEX
    Explanations

    each time

    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
     altri
    0.58
     volumes
    0.52
     estable
    0.51
     stills
    0.51
     oor
    0.50
     courtyard
    0.50
    র
    0.49
    рур
    0.49
    <h2>
    0.49
     propios
    0.48
    POSITIVE LOGITS
    li
    0.69
    kita
    0.65
    마다
    0.63
    遇到
    0.63
    ka
    0.62
    DR
    0.62
    h
    0.62
    kali
    0.61
    k
    0.61
    whenever
    0.57
    Activations Density 0.021%

    No Known Activations