© 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. 57029
    Prev
    Next
    INDEX
    Explanations

    attached content

    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
    <0x80>
    0.53
     дизай
    0.46
    0
    0.43
     سکتا
    0.43
     возраста
    0.43
    nia
    0.43
    компа
    0.43
    ALD
    0.42
    곳
    0.41
    APA
    0.41
    POSITIVE LOGITS
     attached
    1.19
     attach
    1.14
     attaching
    1.05
     attachments
    1.03
     Attached
    1.03
    attach
    1.02
     attachment
    1.00
    attached
    1.00
     Attach
    0.98
    附
    0.95
    Activations Density 0.015%

    No Known Activations