© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116109
    Prev
    Next
    INDEX
    Explanations

    Marra, Marr, or arr followed by specific words

    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
    Those
    -0.78
    Ultimately
    -0.78
    Obviously
    -0.74
     غذایی
    -0.74
     dessus
    -0.73
    Some
    -0.72
     stade
    -0.71
     cautious
    -0.71
    которые
    -0.70
    Initially
    -0.70
    POSITIVE LOGITS
    lrr
    0.93
    pective
    0.92
     náš
    0.89
    ARR
    0.88
     lucru
    0.87
    itres
    0.85
    arr
    0.85
    গু
    0.83
     عمليات
    0.82
    🌯
    0.82
    Activations Density 0.046%

    No Known Activations