© 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. 15398
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by instruction

    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
     Дмитри
    0.40
    adiq
    0.39
     sponsorships
    0.39
    ურთ
    0.39
     levies
    0.38
    ...>
    0.38
     ...(
    0.38
    dler
    0.38
    ारखंड
    0.37
    ...">
    0.35
    POSITIVE LOGITS
     möjligt
    0.41
     maupun
    0.36
     annoncé
    0.35
    সি
    0.35
     produzione
    0.35
    說明
    0.34
    こんな
    0.34
    μοι
    0.34
    高雄
    0.34
     এদিকে
    0.33
    Activations Density 0.004%

    No Known Activations