© 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. 22-GEMMASCOPE-RES-131K
    4. 68641
    Prev
    Next
    INDEX
    Explanations

    market analysis reports

    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_22/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
    房子
    -1.14
     about
    -1.11
     all
    -1.10
    ”,
    -1.09
    』、
    -1.06
     like
    -1.05
     free
    -1.05
    ";
    -1.05
    ům
    -1.04
    });
    -1.03
    POSITIVE LOGITS
    ␮
    1.24
     boulangerie
    1.23
     құ
    1.23
     bril
    1.22
     ayah
    1.19
    ньому
    1.18
     melat
    1.17
     שלנו
    1.14
     chande
    1.13
     désormais
    1.12
    Activations Density 0.004%

    No Known Activations