© 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. 40-GEMMASCOPE-2-RES-262K
    7. 98921
    Prev
    Next
    INDEX
    Explanations

    multilingual topic markers

    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_40_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
     ausz
    0.42
     muck
    0.41
     Cass
    0.40
    Cass
    0.40
     '='
    0.40
     m
    0.38
     Palash
    0.38
     suffoc
    0.38
    â
    0.38
     Cassandra
    0.38
    POSITIVE LOGITS
    렴
    0.43
    媤
    0.41
    லாம்
    0.36
    ेंड
    0.36
    劇場
    0.36
    డిగా
    0.36
    aternity
    0.35
     lavage
    0.35
    ッセ
    0.35
    edges
    0.34
    Activations Density 0.005%

    No Known Activations