© 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. 22-GEMMASCOPE-RES-131K
    7. 28469
    Prev
    Next
    INDEX
    Explanations

    conditional affirmations and suggestions

    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
     tryna
    -1.02
     atriz
    -0.98
    BaseActivity
    -0.91
    ᝰ
    -0.88
    ()<<
    -0.87
     studenti
    -0.85
     rubrique
    -0.84
     geometr
    -0.81
     Consequently
    -0.80
    urator
    -0.80
    POSITIVE LOGITS
    OK
    1.15
     OK
    1.09
     ok
    1.07
    始まり
    1.01
     molded
    0.99
     alright
    0.97
     will
    0.94
     then
    0.92
    Ok
    0.91
     better
    0.89
    Activations Density 0.016%

    No Known Activations