Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13310
    Prev
    Next
    INDEX
    Explanations

    break down or break free

    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_16k_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
    0
    0.61
    <0x80>
    0.58
    0
    0.57
     }^{
    0.55
     населения
    0.54
     ,"
    0.53
     ,
    0.52
    𝚘
    0.52
    I
    0.52
    ՝
    0.51
    POSITIVE LOGITS
     Break
    1.23
     Breaking
    1.23
     breaking
    1.16
     break
    1.16
    Breaking
    1.05
    Break
    1.04
    breakable
    1.02
     Breaks
    1.02
    breaking
    1.01
     BREAK
    0.98
    Activations Density 0.139%

    No Known Activations