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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110526
    Prev
    Next
    INDEX
    Explanations

    words starting with Front

    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
     vùng
    -0.90
    挲
    -0.88
     Пото
    -0.85
     hornear
    -0.84
     shortcomings
    -0.82
    ities
    -0.81
     заключается
    -0.80
     Belast
    -0.80
     оказа
    -0.80
    Oc
    -0.79
    POSITIVE LOGITS
    psin
    1.05
     porch
    1.02
     paws
    1.02
    pium
    0.97
    t
    0.96
    verifyException
    0.93
    utterstock
    0.93
    ]$}
    0.89
     yard
    0.88
    方的
    0.88
    Activations Density 0.027%

    No Known Activations