© 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-262K
    7. 19455
    Prev
    Next
    INDEX
    Explanations

    describing actions or calculations

    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
     facing
    0.43
     last
    0.41
     Daniel
    0.40
     District
    0.39
     Hi
    0.39
    '
    0.39
    .
    0.38
    كان
    0.38
     Tanner
    0.38
     Chuck
    0.38
    POSITIVE LOGITS
    ᱠ
    0.51
    ﻨ
    0.49
     ପ୍ର
    0.48
     ವ್ಯವ
    0.48
    âl
    0.47
     SYSTEMS
    0.46
    💹
    0.46
    Produtos
    0.46
    説明
    0.45
     주장
    0.45
    Activations Density 0.004%

    No Known Activations