© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66895
    Prev
    Next
    INDEX
    Explanations

    radio frequency communication

    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
    哟
    -2.89
     Which
    -2.67
    '
    -2.50
     –
    -2.44
     
    -2.36
     However
    -2.30
    菔
    -2.30
     Of
    -2.30
     aunque
    -2.28
     

    -2.28
    POSITIVE LOGITS
    e
    3.23
    »;
    2.59
     gaf
    2.58
    𓋼
    2.50
    ኧ
    2.48
    鉏
    2.47
    齪
    2.47
     REPRESENTATIVES
    2.45
    覬
    2.45
    ſam
    2.44
    Activations Density 0.021%

    No Known Activations