© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127224
    Prev
    Next
    INDEX
    Explanations

    legal hearings

    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_10/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
    ’
    -2.27
    他又
    -2.14
    d
    -2.05
    ᠂
    -2.02
    and
    -1.98
     और
    -1.95
    “
    -1.94
    j
    -1.94
    および
    -1.92
    และ
    -1.88
    POSITIVE LOGITS
    ↵↵
    2.45
    }$.
    2.31
    ﻂ
    2.22
    􀂃
    2.16
    纮
    2.05
    哢
    2.05
    韪
    1.98
    齪
    1.97
    镔
    1.94
    <bos>
    1.92
    Activations Density 0.008%

    No Known Activations