© 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. 46128
    Prev
    Next
    INDEX
    Explanations

    format, increase, phone, bias, leak

    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
    렬
    0.50
     modul
    0.50
     pluck
    0.48
     rearrange
    0.47
    𐰞
    0.47
    加载
    0.47
    írus
    0.47
     lanjutkan
    0.46
     lodges
    0.46
     persp
    0.46
    POSITIVE LOGITS
     Recorder
    0.45
     Chan
    0.43
    k
    0.43
    afin
    0.43
    denom
    0.42
     Ranch
    0.42
    ia
    0.41
     Bernstein
    0.41
     Bod
    0.41
    ccia
    0.41
    Activations Density 0.012%

    No Known Activations