© 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-262K
    7. 3611
    Prev
    Next
    INDEX
    Explanations

    in conjunction

    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_262k_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
    iest
    0.22
    AN
    0.21
     That
    0.21
    .”
    0.20
    。
    0.20
    grave
    0.19
     inclinations
    0.19
     begann
    0.19
     commandments
    0.19
    М
    0.19
    POSITIVE LOGITS
    舴
    0.23
    牰
    0.22
     Wetlands
    0.22
    㗊
    0.22
    沚
    0.22
    வற்ற
    0.21
    由于
    0.21
    水量
    0.21
    流程
    0.21
    樘
    0.21
    Activations Density 0.000%

    No Known Activations