© 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. 31-GEMMASCOPE-2-RES-262K
    7. 111167
    Prev
    Next
    INDEX
    Explanations

    most dangerous, think about, spreads through

    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
    cevam
    0.49
     rispondere
    0.47
    zoeken
    0.46
    Ⲣ
    0.45
     دوسرا
    0.44
    DBObject
    0.43
    Trav
    0.43
     เดือน
    0.43
    Tanggal
    0.43
     ἡ
    0.43
    POSITIVE LOGITS
    枝
    0.48
    巨
    0.46
    uric
    0.46
    طة
    0.44
    3
    0.44
     giant
    0.43
     spongy
    0.43
     станда
    0.43
    届け
    0.43
     scratching
    0.42
    Activations Density 0.003%

    No Known Activations