© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110474
    Prev
    Next
    INDEX
    Explanations

    return and related actions

    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
     back
    -0.95
    back
    -0.93
    BACK
    -0.92
     Relocation
    -0.91
    encji
    -0.91
     Regeneration
    -0.87
    Back
    -0.84
    removal
    -0.84
    recognition
    -0.80
    անում
    -0.79
    POSITIVE LOGITS
     return
    3.13
     returns
    2.20
     возвра
    1.84
     Return
    1.81
     returned
    1.77
    Return
    1.73
    return
    1.72
    RETURN
    1.60
     retorno
    1.50
    返回值
    1.49
    Activations Density 0.052%

    No Known Activations