© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7286
    Prev
    Next
    INDEX
    Explanations

    break, crack, break up

    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
     BLUEN
    0.41
     сн
    0.40
     NV
    0.39
    ᴱ
    0.39
     strerror
    0.38
    িনীর
    0.38
    Proveedor
    0.38
    訖
    0.37
     चेन
    0.37
    ঞ্ছ
    0.37
    POSITIVE LOGITS
     breaks
    0.62
    breaks
    0.56
     break
    0.47
     Breaks
    0.46
    break
    0.45
     cracks
    0.44
    Break
    0.42
     breakpoints
    0.42
    breakable
    0.42
     Break
    0.41
    Activations Density 0.031%

    No Known Activations