© 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. 10-GEMMASCOPE-RES-131K
    4. 102123
    Prev
    Next
    INDEX
    Explanations

    action followed by a consequence

    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
    <strong>
    -1.17
     gemeinsam
    -1.16
     knowing
    -1.16
     praça
    -1.14
    vri
    -1.11
     Meldung
    -1.09
     three
    -1.08
     these
    -1.04
     ingredienti
    -1.04
     These
    -1.03
    POSITIVE LOGITS
    FontOfSize
    1.16
    razio
    1.15
    ("")){
    1.12
    ropoda
    1.10
     enorme
    1.09
    modèle
    1.09
    unción
    1.05
    cension
    1.05
    }());
    1.05
    传来
    1.05
    Activations Density 0.048%

    No Known Activations