© 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. 6150
    Prev
    Next
    INDEX
    Explanations

    escape or get away

    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
    ED
    0.49
    夶
    0.46
    וס
    0.46
     tenetur
    0.44
    寶寶
    0.44
    ,\"
    0.43
    㤟
    0.43
    ,»
    0.43
    *",
    0.42
    ovaniyu
    0.42
    POSITIVE LOGITS
     escape
    0.61
    at
    0.58
     escapes
    0.54
     circumvent
    0.51
    ↵
    0.50
    escape
    0.50
     escaping
    0.49
     escaped
    0.48
    ა
    0.47
     escapar
    0.46
    Activations Density 0.118%

    No Known Activations