© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30694
    Prev
    Next
    INDEX
    Explanations

    breaking fast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    гин
    -0.81
    ARKS
    -0.73
    र्ट
    -0.71
    inação
    -0.69
    ätze
    -0.66
    tshell
    -0.66
     राष्ट
    -0.65
    ENAME
    -0.65
    𝜎
    -0.65
    urned
    -0.64
    POSITIVE LOGITS
     breaking
    1.80
     Breaking
    1.66
    ftar
    1.61
     break
    1.55
     Break
    1.52
    Breaking
    1.48
     BREAK
    1.47
    breaking
    1.45
    Break
    1.43
     breaks
    1.35
    Activations Density 0.021%

    No Known Activations