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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 12029
    Prev
    Next
    INDEX
    Explanations

    code delimiters or separators

    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
     particularly
    -1.00
    逡
    -0.93
     through
    -0.93
     besonders
    -0.92
    médi
    -0.92
    ったのは
    -0.89
     setAddress
    -0.88
     including
    -0.88
     from
    -0.88
    到这里
    -0.87
    POSITIVE LOGITS
    </code>
    1.04
    https
    1.00
    ständ
    0.99
    /
    0.98
    <
    0.96
    \
    0.96
    </strong>
    0.95
    },
    0.92
    #
    0.90
    "},
    0.88
    Activations Density 0.010%

    No Known Activations