© 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. 91473
    Prev
    Next
    INDEX
    Explanations

    releases and dissipates

    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
    Ва
    0.54
    﨑
    0.50
    商业
    0.50
    缅
    0.47
     handel
    0.47
    좋
    0.46
    เอียด
    0.46
     پست
    0.44
    인
    0.44
    데
    0.44
    POSITIVE LOGITS
     Faculties
    0.47
    lungs
    0.46
     sages
    0.43
     fiercely
    0.43
     Sevilla
    0.42
     bribes
    0.41
     Founding
    0.41
     are
    0.39
     Ire
    0.39
     Helens
    0.39
    Activations Density 0.008%

    No Known Activations