© 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. 55765
    Prev
    Next
    INDEX
    Explanations

    finding next word

    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
    月
    0.54
    拒绝
    0.53
    食物
    0.48
    什麼
    0.47
    變
    0.46
    涉及
    0.45
    事件
    0.45
     चौकी
    0.45
    这一点
    0.44
    酶
    0.44
    POSITIVE LOGITS
    abhavena
    0.55
     будем
    0.52
     theorists
    0.52
    de
    0.51
    anchor
    0.50
     eldest
    0.49
    atthakath
    0.49
    brackets
    0.49
     recognizing
    0.47
    argb
    0.47
    Activations Density 0.003%

    No Known Activations