© 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. 53821
    Prev
    Next
    INDEX
    Explanations

    laws, routes, rulers, time, lengths

    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
    знача
    0.44
     تھے۔
    0.42
    Murray
    0.42
     जिसने
    0.41
    Strange
    0.41
    Bob
    0.41
    מל
    0.40
    铐
    0.40
    Peter
    0.40
    despite
    0.39
    POSITIVE LOGITS
     wax
    0.47
     locomotion
    0.43
     keep
    0.42
     massage
    0.40
     type
    0.40
     multiples
    0.40
     kazi
    0.40
     vü
    0.39
     کال
    0.39
     trink
    0.39
    Activations Density 0.000%

    No Known Activations