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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3137
    Prev
    Next
    INDEX
    Explanations

    current and existing

    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_16_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
     ﺍﻟ
    0.40
    ll
    0.38
    ﻟ
    0.37
    ci
    0.37
    ıp
    0.35
     altre
    0.35
    </h6>
    0.35
     una
    0.35
     も
    0.35
     એક
    0.35
    POSITIVE LOGITS
    Have
    0.29
    Attempts
    0.27
    قق
    0.26
    7
    0.26
    FOUND
    0.25
    s
    0.25
    ድግዳ
    0.25
     mergers
    0.24
    hobby
    0.24
    Anti
    0.24
    Activations Density 0.424%

    No Known Activations