© 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. 13323
    Prev
    Next
    INDEX
    Explanations

    destination pathing

    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
     effray
    -1.27
    –
    -1.23
     inappropriés
    -1.20
    ///////////
    -1.07
     arbeta
    -1.05
    Ջ
    -1.04
     fekete
    -1.02
    acheter
    -1.02
    AllowUser
    -1.02
     började
    -1.02
    POSITIVE LOGITS
    <eos>
    2.00
    .”
    1.17
     }}"></
    1.04
    ."
    1.02
     continue
    0.99
    』。
    0.98
    ,’
    0.97
    次回は
    0.95
    」。
    0.94
    ==""){
    0.94
    Activations Density 0.002%

    No Known Activations