© 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. 109274
    Prev
    Next
    INDEX
    Explanations

    the followed by nouns

    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
     rangka
    -0.85
     own
    -0.85
    ૩
    -0.82
    Описание
    -0.81
     erläut
    -0.81
     мне
    -0.80
    ｀*)
    -0.79
    rd
    -0.78
    now
    -0.76
    Nuestros
    -0.76
    POSITIVE LOGITS
    matically
    1.11
    estars
    0.96
    miste
    0.94
     cukru
    0.92
    ecken
    0.88
    issen
    0.88
    accessToken
    0.86
    vē
    0.85
     Agreements
    0.85
    ifik
    0.85
    Activations Density 0.055%

    No Known Activations