© 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. 34-GEMMASCOPE-RES-131K
    7. 2193
    Prev
    Next
    INDEX
    Explanations

    specialized or technical terms

    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
    凜
    -0.81
    Ton
    -0.76
    gili
    -0.75
    ridged
    -0.75
    ってしまった
    -0.73
    受信
    -0.72
    EMOS
    -0.72
    logr
    -0.71
    mpf
    -0.71
    gnar
    -0.71
    POSITIVE LOGITS
    Reak
    0.85
     néanmoins
    0.83
    Инг
    0.83
    Toute
    0.82
    をチェック
    0.81
    uertos
    0.81
    atile
    0.81
    Dossier
    0.81
    覗
    0.81
    yelitis
    0.80
    Activations Density 0.000%

    No Known Activations