© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 53038
    Prev
    Next
    INDEX
    Explanations

    localhost values Evening

    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
    ט
    0.62
    수
    0.53
    до
    0.52
    או
    0.52
    稒
    0.51
    データを
    0.50
    ಂತಹ
    0.50
    но
    0.49
    РА
    0.49
    う
    0.49
    POSITIVE LOGITS
    养老
    0.44
     HHS
    0.43
     Pension
    0.42
     signifying
    0.42
     coined
    0.42
     Chapman
    0.42
     Liu
    0.41
     sanctuary
    0.41
     Anthology
    0.40
    clusions
    0.40
    Activations Density 0.003%

    No Known Activations