© 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-16K
    7. 10124
    Prev
    Next
    INDEX
    Explanations

    retention efforts

    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_16k_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
    ↵
    0.68
     j
    0.45
     à
    0.44
    之间
    0.42
    fordshire
    0.40
    商业
    0.39
    LocalDateTime
    0.39
    近期
    0.38
    ineuse
    0.38
    onu
    0.38
    POSITIVE LOGITS
     imasmim
    0.51
     exercícios
    0.49
    ಮೇ
    0.48
     patitth
    0.46
     ejercicios
    0.44
     reacciones
    0.44
     pavatt
    0.44
     cittam
    0.43
    <tfoot>
    0.43
    त्व
    0.43
    Activations Density 0.051%

    No Known Activations