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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13310
    Prev
    Next
    INDEX
    Explanations

    breaking out, in, down, through

    np_acts-logits-general · gemini-2.5-flash-lite

    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-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <0x80>
    0.60
    ０
    0.55
    0
    0.54
     населения
    0.47
     }^{
    0.46
    I
    0.45
     -\
    0.45
    ՝
    0.45
    E
    0.44
    まん
    0.43
    POSITIVE LOGITS
     Break
    1.40
     break
    1.31
     Breaking
    1.27
     BREAK
    1.27
     breaking
    1.26
    break
    1.19
     Breaks
    1.19
    Break
    1.18
    破
    1.16
     broke
    1.15
    Activations Density 0.143%

    No Known Activations