Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 9089
    Prev
    Next
    INDEX
    Explanations

    agreement between parties

    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
    來
    -1.04
     カーディガン
    -0.97
     einheit
    -0.93
    ällningar
    -0.92
    combined
    -0.87
     acuarela
    -0.87
    tierung
    -0.86
     développé
    -0.85
    quirrels
    -0.85
     folosit
    -0.85
    POSITIVE LOGITS
     agreements
    1.68
     agreement
    1.65
     between
    1.63
     with
    1.40
     signed
    1.38
     reached
    1.37
     между
    1.31
     Agreement
    1.25
     entered
    1.24
     Agreements
    1.23
    Activations Density 0.039%

    No Known Activations